Loading video...

Video Failed to Load

Go Home

Static obstacles. Sudden door openings. Fallen bikes. XPENG NGP anticipates them all. Continuous, smooth, and effortless avoidance. Tap to watch the uncut XPENG L03 safety test. $XPEV

XPENG_Global's profile picture

XPENG

412,747 subscribers

1,868,473 views • 26 days ago •via X (Twitter)

Science & Technology
LIVE

Anya Rossi• Live Now

Private livecam show

0 Comments

No comments available

Comments from the original post will appear here

Related Videos

Master every spot with the XPENG L03. Remote summon. Trail reverse assist. Customized auto-parking with active obstacle avoidance. Effortless head-in parking at your fingertips. The ultimate all-scenario smart parking expert. $XPEV
1:42

Master every spot with the XPENG L03. Remote summon. Trail reverse assist. Customized auto-parking with active obstacle avoidance. Effortless head-in parking at your fingertips. The ultimate all-scenario smart parking expert. $XPEV

XPENG

1,695,994 views • 22 days ago

Relive the magic. Catch every breathtaking moment of the XPENG L03 global launch. The journey into a new era has just begun. Tap to watch the quick recap. $XPEV
3:36

Relive the magic. Catch every breathtaking moment of the XPENG L03 global launch. The journey into a new era has just begun. Tap to watch the quick recap. $XPEV

XPENG

35,879,450 views • 19 days ago

The XPENG L03 just awakened European streets. Global media experienced NGP for the very first time, unlocking a new era of urban smart driving and leaving them in absolute awe of the future of mobility. $XPEV
2:45

The XPENG L03 just awakened European streets. Global media experienced NGP for the very first time, unlocking a new era of urban smart driving and leaving them in absolute awe of the future of mobility. $XPEV

XPENG

1,444,440 views • 15 days ago

Can our latest AI tech impress Richard Hammond? Whether it's complex intersections, narrow roads, or parking, XPENG anticipates and reacts with total precision. Watch Hammond test the future of mobility. $XPEV
8:46

Can our latest AI tech impress Richard Hammond? Whether it's complex intersections, narrow roads, or parking, XPENG anticipates and reacts with total precision. Watch Hammond test the future of mobility. $XPEV

XPENG

858,076 views • 5 months ago

Global media took the new XPENG P7 on real roads — testing its latest intelligent driving and NGP. From Voice Control to true Door-to-Door navigation, the P7 delivers intelligence in every move. Can it take on FSD? 👇 $XPEV
3:09

Global media took the new XPENG P7 on real roads — testing its latest intelligent driving and NGP. From Voice Control to true Door-to-Door navigation, the P7 delivers intelligence in every move. Can it take on FSD? 👇 $XPEV

XPENG

517,082 views • 8 months ago

In Munich, I took some time to drive XPENG L03 and test the performance of our Next Generation Pilot (NGP) system with Xianming Liu . The results amazed me. Take a look at what we're bringing to European users, an intelligent driving experience designed for local traffic rules and right of way.
4:12

In Munich, I took some time to drive XPENG L03 and test the performance of our Next Generation Pilot (NGP) system with Xianming Liu . The results amazed me. Take a look at what we're bringing to European users, an intelligent driving experience designed for local traffic rules and right of way.

Xiaopeng He

3,436,332 views • 18 days ago

Southeast Asian media put VLA 2.0 to the test on roads that felt just like home — narrow lanes, chaotic traffic, and nonstop complexity. Could XPENG VLA 2.0 win them over? Their verdict: Bring it to Southeast Asia. Now! 🔥 $XPEV
2:36

Southeast Asian media put VLA 2.0 to the test on roads that felt just like home — narrow lanes, chaotic traffic, and nonstop complexity. Could XPENG VLA 2.0 win them over? Their verdict: Bring it to Southeast Asia. Now! 🔥 $XPEV

XPENG

1,077,427 views • 2 months ago

A member in our chat group shared his initial experience with FSD. He just downloaded v13.2.6 after returning back to Shenzhen, China before he took several test drives with FSD engaged and accumulated over 100 km FSD mileage. He is so impressed by the flawless zero-disengagement or zero-intervention drives. He invited his friend, an Xpeng X9 owner, to test it as well. The friend uses XPeng’s latest NGP autonomous driving system all the time. Obviously he is a very savvy ADAS observer in China. After the test drive, his verdict is: FSD is “invincible”. The foundational capabilities of FSD are far better than those of other systems in China. Let that sink in.
1:42

A member in our chat group shared his initial experience with FSD. He just downloaded v13.2.6 after returning back to Shenzhen, China before he took several test drives with FSD engaged and accumulated over 100 km FSD mileage. He is so impressed by the flawless zero-disengagement or zero-intervention drives. He invited his friend, an Xpeng X9 owner, to test it as well. The friend uses XPeng’s latest NGP autonomous driving system all the time. Obviously he is a very savvy ADAS observer in China. After the test drive, his verdict is: FSD is “invincible”. The foundational capabilities of FSD are far better than those of other systems in China. Let that sink in.

Ray

165,079 views • 1 year ago

Autonomous driving and obstacles avoidance at drift speeds, challenging the limits of what is possible! In this demo, our vehicle can be seen performing #autonomousdriving at very high speeds, causing it to both skid and drift at turns, while also avoiding obstacles. At such speeds, given the inherent dynamics of the vehicle platform used, it is very easy for the vehicle to topple. The #reinforcementlearning based motion planning and decision making framework that is being demoed here is tasked with ensuring obstacles avoidance without compromising on the speed, to an extent possible, and to drive the vehicle as fast as possible. This is evident towards the end of the video, where it can be seen that our vehicle avoided static obstacles while drifting.This demonstrates the level of sophistication and agility in our framework to ensure proper control of the #autonomousvehicles at high-speeds. The use cases are many; to begin with, our generic off-roads autonomous driving research focuses on enabling autonomous navigation in previously unknown and unseen environments, while ensuring mathematical completeness guarantees. Such agility can also help on-road autonomous vehicles to deal with unforeseeable corner cases or sudden appearance of obstacles in its tracks, at high-speeds. Our underlying research at Swaayatt Robots is still far from over, and over the next 3-4 months, we will be demonstrating abstract representation being learned by our multi-RL agents based framework (under progress) to ensure computation of the cost of the terrain without any labelled data, where multiple agents learn to control / regulate different aspects of autonomous navigation, to ensure safe and robust navigation, both on- and off-roads. All the people on the ground, who participated in the demo, were trained safety professionals. #deeplearning #MachineLearning #Robotics
3:38

Autonomous driving and obstacles avoidance at drift speeds, challenging the limits of what is possible! In this demo, our vehicle can be seen performing #autonomousdriving at very high speeds, causing it to both skid and drift at turns, while also avoiding obstacles. At such speeds, given the inherent dynamics of the vehicle platform used, it is very easy for the vehicle to topple. The #reinforcementlearning based motion planning and decision making framework that is being demoed here is tasked with ensuring obstacles avoidance without compromising on the speed, to an extent possible, and to drive the vehicle as fast as possible. This is evident towards the end of the video, where it can be seen that our vehicle avoided static obstacles while drifting.This demonstrates the level of sophistication and agility in our framework to ensure proper control of the #autonomousvehicles at high-speeds. The use cases are many; to begin with, our generic off-roads autonomous driving research focuses on enabling autonomous navigation in previously unknown and unseen environments, while ensuring mathematical completeness guarantees. Such agility can also help on-road autonomous vehicles to deal with unforeseeable corner cases or sudden appearance of obstacles in its tracks, at high-speeds. Our underlying research at Swaayatt Robots is still far from over, and over the next 3-4 months, we will be demonstrating abstract representation being learned by our multi-RL agents based framework (under progress) to ensure computation of the cost of the terrain without any labelled data, where multiple agents learn to control / regulate different aspects of autonomous navigation, to ensure safe and robust navigation, both on- and off-roads. All the people on the ground, who participated in the demo, were trained safety professionals. #deeplearning #MachineLearning #Robotics

Sanjeev Sharma

11,181 views • 1 year ago

Autonomous dodging off-roads without any human presence. This is a demonstration of pushing the limits of what is possible in off-road #autonomousdriving. In this demo, we performed autonomous dodging without any human presence in our autonomous vehicle, that too off-roads. In this mode, collision avoidance against aggressive-stochastic-adversarial traffic is the sole responsibility of #AutonomousVehicles. Our autonomous vehicle, Deep Xplorer, was tasked with navigating an off-road trail, avoiding both the static and dynamic obstacles. Furthermore, team members on bikes introduced random cross-traffic interactions by cutting its path at random, creating highly adversarial and stochastic traffic scenarios. To increase the stakes even further, I personally drove our other autonomous vehicle (Xplorer), cutting the path of Deep Xplorer at random --leaving the task of negotiation, motion planning, and decision making, to ensure collision avoidance and safety of the vehicles and the environment as a sole responsibility of our autonomous driving stack in Deep Xplorer. This is the first time in the history of Swaayatt Robots that we performed autonomous dodging without human presence in our autonomous vehicle, pushing the limits of what is possible in autonomous driving landscape. #reinforcementlearning #deeplearning
6:35

Autonomous dodging off-roads without any human presence. This is a demonstration of pushing the limits of what is possible in off-road #autonomousdriving. In this demo, we performed autonomous dodging without any human presence in our autonomous vehicle, that too off-roads. In this mode, collision avoidance against aggressive-stochastic-adversarial traffic is the sole responsibility of #AutonomousVehicles. Our autonomous vehicle, Deep Xplorer, was tasked with navigating an off-road trail, avoiding both the static and dynamic obstacles. Furthermore, team members on bikes introduced random cross-traffic interactions by cutting its path at random, creating highly adversarial and stochastic traffic scenarios. To increase the stakes even further, I personally drove our other autonomous vehicle (Xplorer), cutting the path of Deep Xplorer at random --leaving the task of negotiation, motion planning, and decision making, to ensure collision avoidance and safety of the vehicles and the environment as a sole responsibility of our autonomous driving stack in Deep Xplorer. This is the first time in the history of Swaayatt Robots that we performed autonomous dodging without human presence in our autonomous vehicle, pushing the limits of what is possible in autonomous driving landscape. #reinforcementlearning #deeplearning

Sanjeev Sharma

68,257 views • 5 months ago

Autonomous vehicle learning to dodge traffic, performing stochastic adversarial negotiation. On 27th August we had representatives from the Suzuki Motor Corporation's autonomous department, Genki Maeda (Department Manager, AD Platform Development), Karachi Nobunari (Department General Manager, Advance Technology Development Department) and Ronit Kumar (Suzuki Innovation Center) visit us to test our #autonomousdriving technology. This was a high-stakes demo, where we asked our engineering team (including the founder, Sanjeev Sharma) to ride two wheeler and to cut the path of our autonomous vehicle at random / at will, in a live demo, creating an adversarial scenario, where it is the sole responsibility of our autonomous vehicle to dodge obstacles and prevent accidents. Over the years, we have been building autonomous driving technology to enable negotiation of adversarial-complex-stochastic traffic dynamics. This demo is only a short trailer of what is being developed and what is going to come next. We made the vehicle first negotiate randomly placed static vehicles, bikes and cones on the road. Then in the next section of the road, our engineering team started cutting the path of autonomous vehicle at random, and let it take care of obstacles avoidance and negotiation, balancing aggressiveness and passivity. These algorithmic frameworks are being scaled up to achieve Level-4 and Level-5 autonomous driving, in the most complex of traffic situations imaginable in the world for #autonomousvehicles, i.e., Indian traffic on Indian roads, to conquer this space globally. The speed of the vehicle was kept low in this demo, keeping in mind the safety of the guests. The core motion planning and decision making algorithm in the demo utilized one #reinforcementlearning agent. There is going to be another demo on similar lines next week, on an extended stretch of a road. #deeplearning #India
4:55

Autonomous vehicle learning to dodge traffic, performing stochastic adversarial negotiation. On 27th August we had representatives from the Suzuki Motor Corporation's autonomous department, Genki Maeda (Department Manager, AD Platform Development), Karachi Nobunari (Department General Manager, Advance Technology Development Department) and Ronit Kumar (Suzuki Innovation Center) visit us to test our #autonomousdriving technology. This was a high-stakes demo, where we asked our engineering team (including the founder, Sanjeev Sharma) to ride two wheeler and to cut the path of our autonomous vehicle at random / at will, in a live demo, creating an adversarial scenario, where it is the sole responsibility of our autonomous vehicle to dodge obstacles and prevent accidents. Over the years, we have been building autonomous driving technology to enable negotiation of adversarial-complex-stochastic traffic dynamics. This demo is only a short trailer of what is being developed and what is going to come next. We made the vehicle first negotiate randomly placed static vehicles, bikes and cones on the road. Then in the next section of the road, our engineering team started cutting the path of autonomous vehicle at random, and let it take care of obstacles avoidance and negotiation, balancing aggressiveness and passivity. These algorithmic frameworks are being scaled up to achieve Level-4 and Level-5 autonomous driving, in the most complex of traffic situations imaginable in the world for #autonomousvehicles, i.e., Indian traffic on Indian roads, to conquer this space globally. The speed of the vehicle was kept low in this demo, keeping in mind the safety of the guests. The core motion planning and decision making algorithm in the demo utilized one #reinforcementlearning agent. There is going to be another demo on similar lines next week, on an extended stretch of a road. #deeplearning #India

Swaayatt Robots

22,375 views • 11 months ago

STARSHIP V3 SHIP 39: THE REUSE AUDITION BEGINS Everyone watches launches. Engineers watch the tests before them. Ship 39 just rolled from Mega Bay 2 to Massey’s test stand – engine bay empty on purpose. The Test Ladder: * Rollout complete – Ship 39 now sitting at Massey’s dedicated test stand * Cryo proof testing – tanks filled with liquid nitrogen to simulate brutal flight conditions * Pressure cycles – checking domes, tank walls, thrust structure and leaks * Structural stress – proving the ship can survive real propellant loads Pass that test and the real fun starts: * Install 6 Raptor 3 engines * Move to Orbital Launch Pad 2 * Full propellant load – liquid oxygen + methane * Static fires – first single engine, then all six This one is different. Ship 39 is the first flight-ready Block 3 Starship – taller, stronger, and built for reuse. If testing holds, it flies with Booster 19 on Flight 12. Target: March 2026. Source: Grok SpaceX
0:32

STARSHIP V3 SHIP 39: THE REUSE AUDITION BEGINS Everyone watches launches. Engineers watch the tests before them. Ship 39 just rolled from Mega Bay 2 to Massey’s test stand – engine bay empty on purpose. The Test Ladder: * Rollout complete – Ship 39 now sitting at Massey’s dedicated test stand * Cryo proof testing – tanks filled with liquid nitrogen to simulate brutal flight conditions * Pressure cycles – checking domes, tank walls, thrust structure and leaks * Structural stress – proving the ship can survive real propellant loads Pass that test and the real fun starts: * Install 6 Raptor 3 engines * Move to Orbital Launch Pad 2 * Full propellant load – liquid oxygen + methane * Static fires – first single engine, then all six This one is different. Ship 39 is the first flight-ready Block 3 Starship – taller, stronger, and built for reuse. If testing holds, it flies with Booster 19 on Flight 12. Target: March 2026. Source: Grok SpaceX

Mario Nawfal

23,929 views • 4 months ago

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:
1:33

NEWS: Waymo has released a new blog post detailing their AI strategy and how it’s allowing them to bring service to more riders faster. "Achieving demonstrably safe AI — where safety is proven, not just promised — requires a holistic approach. Beyond a smart and capable Driver, you also need a closed-loop, realistic Simulator to train and rigorously test the Driver in a myriad of challenging situations, and a sharp Critic to evaluate the Driver's performance and identify areas for improvement." Waymo says that autonomous driving isn’t just a matter of building a “smart driver,” but rather creating a full AI ecosystem centered on safety from the ground up. At the core is the Waymo Foundation Model, a unified world-model that powers all major components of Waymo’s autonomous stack (Driver, Simulator, Critic). "By using a “Think Fast/Think Slow” architecture (combining rapid sensor-fusion with deep semantic reasoning), this system enables the car to detect complex and rare road scenarios (e.g. a burning vehicle ahead), reason about them, and choose safe behavior. Waymo trains large “Teacher” AI-models for driving, simulation, and evaluation, then distills them into smaller, efficient “Student” models suitable for real-world deployment, while keeping safety validation tightly integrated. The result is a continuous “flywheel” of learning: driving data (real and simulated) generate feedback, which leads to refinements, more simulation, more data, and only when safety checks pass is new code deployed. Having already exceeded 100 million fully autonomous miles, Waymo reports a more than ten-fold reduction in severe-injury crashes compared to human drivers." Full blog post:

Sawyer Merritt

83,625 views • 7 months ago

🚨MUST WATCH: The Australian push towards Internet Censorship ID Verification goes even further than you think. Under this law Google Maps, Apple Maps, Searches, YouTube, Rumble, video streaming, etc. will ALL require *ID verification* and *continuous biometric verification* On top of that, these providers would be required to consult with an academic "censorship group," once a year to be told what constitutes "appropriate material," or not. This means a completely controlled onethink system dictated from the top by agenda driven politicians "academics" who get to dictate cultural norms while you are literally forced to comply. All of this under the guise of "child safety," which is obviously important so it becomes an irrefutable excuse to strip freedoms away from you while stifling all dissent because "Are you against child safety?" If you resist -- they have all of your biometric data and see the UK for an example of what happens if you say the wrong things online. Scary stuff! Cherish your freedoms while you have them. 📸source: Aus Integrity
5:06

🚨MUST WATCH: The Australian push towards Internet Censorship ID Verification goes even further than you think. Under this law Google Maps, Apple Maps, Searches, YouTube, Rumble, video streaming, etc. will ALL require *ID verification* and *continuous biometric verification* On top of that, these providers would be required to consult with an academic "censorship group," once a year to be told what constitutes "appropriate material," or not. This means a completely controlled onethink system dictated from the top by agenda driven politicians "academics" who get to dictate cultural norms while you are literally forced to comply. All of this under the guise of "child safety," which is obviously important so it becomes an irrefutable excuse to strip freedoms away from you while stifling all dissent because "Are you against child safety?" If you resist -- they have all of your biometric data and see the UK for an example of what happens if you say the wrong things online. Scary stuff! Cherish your freedoms while you have them. 📸source: Aus Integrity

Autism Capital 🧩

96,320 views • 1 year ago

Gemini 2.5 Flash demolishes my Galton Board test, I could not get 4omini, 4o mini high, or 03 to produce this. I found that Gemini 2.5 Flash understands my intents almost instantly, code produced is tight and neat. The prompt is a merging of various steps. It took me 5 steps to achieve this in Gemini 2.5 Flash, I gave up on OpenAI models after about half an hour. My iterations are obviously not exact. But people can test with this one prompt for more objective comparison. Please try this prompt on your end to confirm: -------------------------------------------------- Create a self-contained HTML file for a Galton board simulation using client-side JavaScript and a 2D physics engine (like Matter.js, included via CDN). The simulation should be rendered on an HTML5 canvas and meet the following criteria: 1. **Single File:** All necessary HTML, CSS, and JavaScript code must be within this single `.html` file. 2. **Canvas Size:** The overall simulation area (canvas) should be reasonably sized to fit on a standard screen without requiring extensive scrolling or zooming (e.g., around 500x700 pixels). 3. **Physics:** Utilize a 2D rigid body physics engine for realistic ball-peg and ball-wall interactions. 4. **Obstacles (Pegs):** Create static, circular pegs arranged in full-width horizontal rows extending across the usable width of the board (not just a triangle). The pegs should be small enough and spaced appropriately for balls to navigate and bounce between them. 5. **Containment:** * Include static, sufficiently thick side walls and a ground at the bottom to contain the balls within the board. * Implement *physical* static dividers between the collection bins at the bottom. These dividers must be thick enough to prevent balls from passing through them, ensuring accurate accumulation in each bin. 6. **Ball Dropping:** Balls should be dropped from a controlled, narrow area near the horizontal center at the top of the board to ensure they enter the peg field consistently. 7. **Bins:** The collection area at the bottom should be divided into distinct bins by the physical dividers. The height of the bins should be sufficient to clearly visualize the accumulation of balls. 8. **Visualization:** Use a high-contrast color scheme to clearly distinguish between elements. Specifically, use yellow for the structural elements (walls, top guides, physical bin dividers, ground), a contrasting color (like red) for the pegs, and a highly contrasting color (like dark grey or black) for the balls. 9. **Demonstration:** The simulation should visually demonstrate the formation of the normal (or binomial) distribution as multiple balls fall through the pegs and collect in the bins. Ensure the physics parameters (restitution, friction, density) and ball drop rate are tuned for a smooth and clear demonstration of the distribution. #OpenAI Sam Altman Greg Brockman AshutoshShrivastava Aidan McLaughlin
0:44

Gemini 2.5 Flash demolishes my Galton Board test, I could not get 4omini, 4o mini high, or 03 to produce this. I found that Gemini 2.5 Flash understands my intents almost instantly, code produced is tight and neat. The prompt is a merging of various steps. It took me 5 steps to achieve this in Gemini 2.5 Flash, I gave up on OpenAI models after about half an hour. My iterations are obviously not exact. But people can test with this one prompt for more objective comparison. Please try this prompt on your end to confirm: -------------------------------------------------- Create a self-contained HTML file for a Galton board simulation using client-side JavaScript and a 2D physics engine (like Matter.js, included via CDN). The simulation should be rendered on an HTML5 canvas and meet the following criteria: 1. **Single File:** All necessary HTML, CSS, and JavaScript code must be within this single `.html` file. 2. **Canvas Size:** The overall simulation area (canvas) should be reasonably sized to fit on a standard screen without requiring extensive scrolling or zooming (e.g., around 500x700 pixels). 3. **Physics:** Utilize a 2D rigid body physics engine for realistic ball-peg and ball-wall interactions. 4. **Obstacles (Pegs):** Create static, circular pegs arranged in full-width horizontal rows extending across the usable width of the board (not just a triangle). The pegs should be small enough and spaced appropriately for balls to navigate and bounce between them. 5. **Containment:** * Include static, sufficiently thick side walls and a ground at the bottom to contain the balls within the board. * Implement *physical* static dividers between the collection bins at the bottom. These dividers must be thick enough to prevent balls from passing through them, ensuring accurate accumulation in each bin. 6. **Ball Dropping:** Balls should be dropped from a controlled, narrow area near the horizontal center at the top of the board to ensure they enter the peg field consistently. 7. **Bins:** The collection area at the bottom should be divided into distinct bins by the physical dividers. The height of the bins should be sufficient to clearly visualize the accumulation of balls. 8. **Visualization:** Use a high-contrast color scheme to clearly distinguish between elements. Specifically, use yellow for the structural elements (walls, top guides, physical bin dividers, ground), a contrasting color (like red) for the pegs, and a highly contrasting color (like dark grey or black) for the balls. 9. **Demonstration:** The simulation should visually demonstrate the formation of the normal (or binomial) distribution as multiple balls fall through the pegs and collect in the bins. Ensure the physics parameters (restitution, friction, density) and ball drop rate are tuned for a smooth and clear demonstration of the distribution. #OpenAI Sam Altman Greg Brockman AshutoshShrivastava Aidan McLaughlin

RameshR

247,923 views • 1 year ago

Today we're unveiling something truly extraordinary—one of the coolest and most transformative technologies: Mixed Reality Testing (MRT). Since launching Waabi World four years ago, we've been building towards this pivotal moment - bringing our virtual testing capabilities into the physical world to fundamentally transform what's possible in autonomous vehicle development. For over 100 years, closed-course testing has been the staple of vehicle safety testing. But creating scenarios on a physical test track resembles elaborate movie-stunts—it’s difficult to reproduce tests consistently, those tests do not capture the diversity of the real-world, and the range of safety-critical scenarios we can test is very limited because of the risk of damaging equipment or, worse, endangering lives. MRT changes everything! In the same way that augmented reality goggles blend the physical world with a virtual world, MRT enables the Waabi Driver to drive autonomously down a physical test track while simultaneously experiencing numerous intelligent, simulated actors that coexist in this hybrid reality and react to each other and to the physical world in naturalistic ways. All this is possible by leveraging Onboard Waabi World, a version of Waabi's neural simulator that runs in a few milliseconds on the onboard compute. As Onboard Waabi World generates new scenarios, the real physical sensor readings are modified instantaneously so the Waabi Driver can react to the blend of real and virtual elements while driving in the physical world. This fusion creates a first-of-its-kind reality that unlocks unlimited testing possibilities previously impossible to achieve safely or practically. Traffic jams can materialize instantly, motorcycles can weave between lanes, crowds of pedestrians can jaywalk unpredictably, children can dart into the street from behind parked cars, animals can wander across the road, debris can appear in lanes creating hazardous obstacles. The possibilities are endless. This breakthrough eliminates all traditional constraints of closed-course testing. We can do exponentially more tests than ever before and in a continuous fashion, with extraordinary levels of diversity and realism. Most importantly, we can push the boundaries of safety testing without real-world consequences. MRT represents the culmination of years of work toward safe, scalable autonomous deployment. It's been central to our testing approach for over two years and fundamental to achieving feature-complete autonomous driving capabilities earlier this year. But this is just the beginning. MRT’s impact extends beyond self-driving trucks – we’re laying the foundation for a future where any physical AI system can be tested and validated safely - from robotaxis to humanoid robots, manufacturing automation to healthcare robotics. Learn about Mixed Reality Testing:
3:45

Today we're unveiling something truly extraordinary—one of the coolest and most transformative technologies: Mixed Reality Testing (MRT). Since launching Waabi World four years ago, we've been building towards this pivotal moment - bringing our virtual testing capabilities into the physical world to fundamentally transform what's possible in autonomous vehicle development. For over 100 years, closed-course testing has been the staple of vehicle safety testing. But creating scenarios on a physical test track resembles elaborate movie-stunts—it’s difficult to reproduce tests consistently, those tests do not capture the diversity of the real-world, and the range of safety-critical scenarios we can test is very limited because of the risk of damaging equipment or, worse, endangering lives. MRT changes everything! In the same way that augmented reality goggles blend the physical world with a virtual world, MRT enables the Waabi Driver to drive autonomously down a physical test track while simultaneously experiencing numerous intelligent, simulated actors that coexist in this hybrid reality and react to each other and to the physical world in naturalistic ways. All this is possible by leveraging Onboard Waabi World, a version of Waabi's neural simulator that runs in a few milliseconds on the onboard compute. As Onboard Waabi World generates new scenarios, the real physical sensor readings are modified instantaneously so the Waabi Driver can react to the blend of real and virtual elements while driving in the physical world. This fusion creates a first-of-its-kind reality that unlocks unlimited testing possibilities previously impossible to achieve safely or practically. Traffic jams can materialize instantly, motorcycles can weave between lanes, crowds of pedestrians can jaywalk unpredictably, children can dart into the street from behind parked cars, animals can wander across the road, debris can appear in lanes creating hazardous obstacles. The possibilities are endless. This breakthrough eliminates all traditional constraints of closed-course testing. We can do exponentially more tests than ever before and in a continuous fashion, with extraordinary levels of diversity and realism. Most importantly, we can push the boundaries of safety testing without real-world consequences. MRT represents the culmination of years of work toward safe, scalable autonomous deployment. It's been central to our testing approach for over two years and fundamental to achieving feature-complete autonomous driving capabilities earlier this year. But this is just the beginning. MRT’s impact extends beyond self-driving trucks – we’re laying the foundation for a future where any physical AI system can be tested and validated safely - from robotaxis to humanoid robots, manufacturing automation to healthcare robotics. Learn about Mixed Reality Testing:

Raquel Urtasun

13,106 views • 1 year ago

🚨BREAKING: ICE agents, working with state police, pulled over a vehicle, in Ogden, Utah… and smashed their car window because he wouldn’t roll it down all the way. Watch the shift… because this is where it goes from aggressive to completely out of control. The driver already has the window partially open. The ICE agent is yelling, giving a countdown, threatening to break the window… while another officer is trying to open the door from the other side. No explanation, or clear threat… Just escalation. Then, someone inside says, “I’m a U.S. citizen… you pointed a gun at me.” And that’s the moment everything changes. Instead of pulling back… instead of correcting… instead of even acknowledging it… The ICE agent snaps. “I don’t give a shit who you are, I don’t know you.” And then he immediately escalates further… raises the metal bar… and starts hitting the window… doubling down on force. A person says you pointed a gun at them… and your response is not to de-escalate… It’s to get MORE aggressive. That’s retaliation. They call them “non-compliant”… and within seconds, the window is smashed and the driver is dragged out. And it doesn’t stop there. The passenger… who is recording… gets told to “stay there” while the officer puts his hand on his gun. He responds, “I’m recording for my safety.” The officer shuts the door on him anyway. When he opens it again and steps out… and then the officer physically shoves him back into the car. This is what needs to be understood… The escalation didn’t come from a threat. It came the second someone spoke up… the second someone said, “you pointed a gun at me”… The second someone started documenting it. That’s when it got worse. That’s when it turned physical. That’s when the window broke. And that’s what should alarm people… because that’s not about safety anymore. That’s about being challenged… and responding with more force.
1:32

🚨BREAKING: ICE agents, working with state police, pulled over a vehicle, in Ogden, Utah… and smashed their car window because he wouldn’t roll it down all the way. Watch the shift… because this is where it goes from aggressive to completely out of control. The driver already has the window partially open. The ICE agent is yelling, giving a countdown, threatening to break the window… while another officer is trying to open the door from the other side. No explanation, or clear threat… Just escalation. Then, someone inside says, “I’m a U.S. citizen… you pointed a gun at me.” And that’s the moment everything changes. Instead of pulling back… instead of correcting… instead of even acknowledging it… The ICE agent snaps. “I don’t give a shit who you are, I don’t know you.” And then he immediately escalates further… raises the metal bar… and starts hitting the window… doubling down on force. A person says you pointed a gun at them… and your response is not to de-escalate… It’s to get MORE aggressive. That’s retaliation. They call them “non-compliant”… and within seconds, the window is smashed and the driver is dragged out. And it doesn’t stop there. The passenger… who is recording… gets told to “stay there” while the officer puts his hand on his gun. He responds, “I’m recording for my safety.” The officer shuts the door on him anyway. When he opens it again and steps out… and then the officer physically shoves him back into the car. This is what needs to be understood… The escalation didn’t come from a threat. It came the second someone spoke up… the second someone said, “you pointed a gun at me”… The second someone started documenting it. That’s when it got worse. That’s when it turned physical. That’s when the window broke. And that’s what should alarm people… because that’s not about safety anymore. That’s about being challenged… and responding with more force.

Jesus Freakin Congress

796,578 views • 4 months ago

How does FSD handle a power outage? Plus: F-150 Lightning cancelled, EV cost breakdown, and more. FSD v14.2.1.25 Narrated Drive 🚘 On this drive, I cover over 200km with ZERO interventions. Because FSD is getting so good, I also break down the latest Tesla and EV news during the trip. Watch the car drive itself while catching up on this week’s updates! Chapters 0:00 FSD 14.2.1.25 Intro 2:20 Cybertruck Demo Drive Reactions & Rivian Comparison 5:13 Testing FSD Profiles: Standard vs. Hurry Speed Caps 7:18 Addressing Lane Change Hesitation & Regressions 8:40 FSD v14.2 Safety vs. v13 on Highways 9:46 BC Highway Flooding & Road Conditions 10:31 Variable Speed Corridors: Does FSD Read Them? 11:41 Highway Lane Discipline & Truck Interaction 12:45 Who watches this channel? 13:40 LFP Battery Efficiency & Charging Costs in BC 15:55 Austin Robotaxi Sightings & Autonomous Testing 18:02 Ford F-150 Lightning Discontinued News 19:05 Return Trip & FSD Criticism Response 20:40 XPeng Parking Tech vs. Tesla Vision 24:33 Mad Max Mode Highway Speed Test 26:50 Navigating Construction Zones & Map Data Issues 28:52 Handling Broken Traffic Lights (Uncontrolled Intersection) 29:40 Final Verdict: 231km Zero Intervention Drive
30:40

How does FSD handle a power outage? Plus: F-150 Lightning cancelled, EV cost breakdown, and more. FSD v14.2.1.25 Narrated Drive 🚘 On this drive, I cover over 200km with ZERO interventions. Because FSD is getting so good, I also break down the latest Tesla and EV news during the trip. Watch the car drive itself while catching up on this week’s updates! Chapters 0:00 FSD 14.2.1.25 Intro 2:20 Cybertruck Demo Drive Reactions & Rivian Comparison 5:13 Testing FSD Profiles: Standard vs. Hurry Speed Caps 7:18 Addressing Lane Change Hesitation & Regressions 8:40 FSD v14.2 Safety vs. v13 on Highways 9:46 BC Highway Flooding & Road Conditions 10:31 Variable Speed Corridors: Does FSD Read Them? 11:41 Highway Lane Discipline & Truck Interaction 12:45 Who watches this channel? 13:40 LFP Battery Efficiency & Charging Costs in BC 15:55 Austin Robotaxi Sightings & Autonomous Testing 18:02 Ford F-150 Lightning Discontinued News 19:05 Return Trip & FSD Criticism Response 20:40 XPeng Parking Tech vs. Tesla Vision 24:33 Mad Max Mode Highway Speed Test 26:50 Navigating Construction Zones & Map Data Issues 28:52 Handling Broken Traffic Lights (Uncontrolled Intersection) 29:40 Final Verdict: 231km Zero Intervention Drive

Devin Olsen

37,995 views • 7 months ago

K1 De Ultimate -Valuejet You all should watch these 2 videos with close attention Frame 1: You can see there are a lot of ground handling operators and aircraft security on ground with K1, definitely talking to him and begging him . Note all passengers have boarded and the door closed, Pilot just needs to communicate with the ATC and push forward to enter the runway for takeoff Watch closely the Aircraft moved forward a little and you can see K1 trying to stopped it , definitely he didn't want them to go because he wasn't allowed to board the plane Frame 2 : You would see that the numbers of people around the aircraft has reduced and K1 was still there with few ground operators still trying to let him know he needs to leave that vicinity, but no he didn't. In aviation, the Pilot have the right to disembark a passenger Annex 6 (Operation of Aircraft) – mandates the *pilot-in-command* has the authority to refuse a passenger or request their removal if safety is at risk. Listen to the voice in frame 2 when the aircraft moved forward: the person said wait now, wait now, shebi you dey block the plane (refering to K1) Definitely they have been dragging the matter and begging him for long which he declined and not letting the pilot to move further. 2 things: 1. They captains might not know they were still there if you compare the numbers of people you see in video 1 and 2 because captains hardly see people they are close to the aircraft nose 2. Out of frustration the captain might decide to move forward to position himself for takeoff Aviation are guided by law and proper investigation needs to be carried out
2:03

K1 De Ultimate -Valuejet You all should watch these 2 videos with close attention Frame 1: You can see there are a lot of ground handling operators and aircraft security on ground with K1, definitely talking to him and begging him . Note all passengers have boarded and the door closed, Pilot just needs to communicate with the ATC and push forward to enter the runway for takeoff Watch closely the Aircraft moved forward a little and you can see K1 trying to stopped it , definitely he didn't want them to go because he wasn't allowed to board the plane Frame 2 : You would see that the numbers of people around the aircraft has reduced and K1 was still there with few ground operators still trying to let him know he needs to leave that vicinity, but no he didn't. In aviation, the Pilot have the right to disembark a passenger Annex 6 (Operation of Aircraft) – mandates the *pilot-in-command* has the authority to refuse a passenger or request their removal if safety is at risk. Listen to the voice in frame 2 when the aircraft moved forward: the person said wait now, wait now, shebi you dey block the plane (refering to K1) Definitely they have been dragging the matter and begging him for long which he declined and not letting the pilot to move further. 2 things: 1. They captains might not know they were still there if you compare the numbers of people you see in video 1 and 2 because captains hardly see people they are close to the aircraft nose 2. Out of frustration the captain might decide to move forward to position himself for takeoff Aviation are guided by law and proper investigation needs to be carried out

Hon.Ab Faj (FlyingAeroBoy)

161,569 views • 1 year ago

Do you ride a bike? Or an e-scooter? Or walk a dog? If so, please take a second to read this. If you are on a bike or scooter on a shared pathway and approaching someone walking a dog, please be courteous and slow down a little. Especially if coming up from behind. I am a wheelchair user with a dog and we have way too many close calls with fast moving bikes and scooters. People not using a bell and whipping by within inches. If the dog turned it's head or stepped a bit wide, they'd be hit. I'll happily move as far to one side of the path as possible, and if I've got the younger dog who isn't as experienced around fast moving things, I'll stop at the very side and have him sit in front of me to give everyone as much space as possible. If I don't know you're approaching, I can't do that. So please, for the love of dog, use your bell. Don't wait until you're right behind someone with a dog. Use it while you're still at a distance, and if you aren't sure they noticed it, ring it a few more times. Give them as much time as possible to move to the side and prepare the dog. If it's a puppy or a dog that hasn't had much experience with bikes, being able to get them off the path or give them a little extra distance from the fast moving bike helps prevent them from getting scared. The vast majority of cyclists are great and really respectful, but there's always a few that aren't. This year the challenge is kids on e-scooters. They are going fast and having fun. Safety isn't at the forefront of their mind. They often don't use a bell or slow down at blind corners, and many don't think about giving the dog any space. I've been startled a few times by them so I can only imagine how the dog felt. This is one of the reasons why I do a lot of desensitization and counter conditioning. Dog owners-you need to do your part to. If you've got headphones on, make sure you can still hear the bike bell. Make sure to give the cyclist or scooter rider as much space as possible from your dog. And of course, unless you are on a designated off leash trail, keep your dog on a leash. If you have a puppy or a newly adopted dog that might not be comfortable around bikes, take some kibble or treats and go hang out with them near a multi use path. Let them watch. As the bike or scooter approaches, drop a few treats on the ground. For many dogs, this is all it takes, but if your dog is visibly stressed, fixated on the bike, or reacting, try moving a further from the trail and once they're comfortable at a slightly further distance, try closer again. If they are still stressed or fearful even with more distance, don't force the issue. Instead introduce them to a bike that isn't moving, and gradually work them up from there. If they are struggling, talk to a trainer. Regardless of if you are holding a leash, riding a bike or scooter, or enjoying a walk outdoors, just be respectful. And of course, be safe. Thanks, Admin 🎥 Puppy walk for cuteness
0:33

Do you ride a bike? Or an e-scooter? Or walk a dog? If so, please take a second to read this. If you are on a bike or scooter on a shared pathway and approaching someone walking a dog, please be courteous and slow down a little. Especially if coming up from behind. I am a wheelchair user with a dog and we have way too many close calls with fast moving bikes and scooters. People not using a bell and whipping by within inches. If the dog turned it's head or stepped a bit wide, they'd be hit. I'll happily move as far to one side of the path as possible, and if I've got the younger dog who isn't as experienced around fast moving things, I'll stop at the very side and have him sit in front of me to give everyone as much space as possible. If I don't know you're approaching, I can't do that. So please, for the love of dog, use your bell. Don't wait until you're right behind someone with a dog. Use it while you're still at a distance, and if you aren't sure they noticed it, ring it a few more times. Give them as much time as possible to move to the side and prepare the dog. If it's a puppy or a dog that hasn't had much experience with bikes, being able to get them off the path or give them a little extra distance from the fast moving bike helps prevent them from getting scared. The vast majority of cyclists are great and really respectful, but there's always a few that aren't. This year the challenge is kids on e-scooters. They are going fast and having fun. Safety isn't at the forefront of their mind. They often don't use a bell or slow down at blind corners, and many don't think about giving the dog any space. I've been startled a few times by them so I can only imagine how the dog felt. This is one of the reasons why I do a lot of desensitization and counter conditioning. Dog owners-you need to do your part to. If you've got headphones on, make sure you can still hear the bike bell. Make sure to give the cyclist or scooter rider as much space as possible from your dog. And of course, unless you are on a designated off leash trail, keep your dog on a leash. If you have a puppy or a newly adopted dog that might not be comfortable around bikes, take some kibble or treats and go hang out with them near a multi use path. Let them watch. As the bike or scooter approaches, drop a few treats on the ground. For many dogs, this is all it takes, but if your dog is visibly stressed, fixated on the bike, or reacting, try moving a further from the trail and once they're comfortable at a slightly further distance, try closer again. If they are still stressed or fearful even with more distance, don't force the issue. Instead introduce them to a bike that isn't moving, and gradually work them up from there. If they are struggling, talk to a trainer. Regardless of if you are holding a leash, riding a bike or scooter, or enjoying a walk outdoors, just be respectful. And of course, be safe. Thanks, Admin 🎥 Puppy walk for cuteness

Team Servicerottie🇨🇦🐕‍🦺🦽

15,632 views • 25 days ago