Sanjeev Sharma
@sanjeevs_iitr • 6,512 subscribers
Founder & CEO: Swaayatt Robot (Autonomous Driving), Deep Eigen (Deep Online Education) Alma Mater: IIT Roorkee, University of Alberta
Videos
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 Sharma68,144 просмотров • 3 месяцев назад
Autonomous driving through very dense dynamic traffic, with extremely tight-complex-stochastic traffic-dynamics on sub-urban roads, connecting to an open ground, with absolutely zero traffic-rules. This is the most heavily cluttered environment where we have tested our #autonomousdriving technology, presenting many of the adversarial negotiation scenarios as well, throughout the autonomous navigation task. This demo was done at the Mata Baglamukhi Madir campus in the city of Nalkheda, in MP, India, and was done in the presence of heavy police forces deployed that day on the ground, as can be seen in our demo. Our autonomous vehicle starts from the temple with a generic open environment, with zero traffic rules, with very narrow corridors created out of barricades for vehicles movement by the security forces. In the corridor no two vehicles can pass through at the same time, and our vehicle was tasked with driving through this corridor, while negotiating its way from any traffic, two-wheelers, or pedestrians it faces, with dense presence of bikes and cars on either side, presenting a very challenging environment for #autonomousvehicles. The vehicle exits the open area, and then assumes generic dual lane navigation, avoiding both static and dynamic obstacles, before encountering a police check-post, where the vehicle is supposed to wait if the barricade is closed, and proceed if open. Upon exiting the checkpost, the vehicle negotiates a traffic-intersection with stochastic and adversarial driving behaviour of other vehicles on the road. Our vehicle continuously faced heavily cluttered traffic scene, where entities on the road can execute a random driving pattern, making the decision making task very challenging. We did the demo over a period of two days, successfully executing multiple (30+) trials in this setting. This demo was again a culmination of our prior works and demos: Kankali Kali Mata demo, on-roads, bidirectional negotiation capability on single lane roads, and open environment Level-5 negotiation capability as showcased in our Toll-Plaza demo. We again scaled up classical decision making and motion planning algorithmic framework, to adapt to such a level of density of obstacles on the road. This framework is further being scaled up with #reinforcementlearning and unsupervised #deeplearning at Swaayatt Robots. We will again do a demo in the month of June here, showcasing autonomously acquired skills to pave the way for Level-5 autonomous driving, and to solve the Level-4 autonomy problem by the end of 2024. #MachineLearning
Sanjeev Sharma332,875 просмотров • 2 лет назад
Autonomous driving through tight, dynamic, stochastic, and adversarial traffic-dynamics on sub-urban roads in India, as well as through partially unstructured environments. This demos showcases the robustness of our motion planning and decision making algorithmic frameworks in enabling #autonomousdriving through seamlessly through such traffic and environmental scenarios. The vehicle starts from a generic open environment at the temple, where there are no traffic-rules to abide by. It then exits the region and assumes a generic autonomous navigation behaviour, negotiating complex traffic scenes. At various points it can be seen that the other vehicles (bikes, autos, bicyclists, and cars) didn't abide by any traffic-rule and moved in crisscross fashion, presenting adversarial scenarios, challenging our autonomous vehicle at Swaayatt Robots to take care of the collision avoidance. This classical motion planning and decision making algorithmic framework is being further scaled up with deep #reinforcementlearning, which will practically solve the sub-urban traffic-dynamics and environment negotiation for #autonomousvehicles in India and throughout the world as well. This demo was done at the Kankali Kali Mata mandir in the city of Bhopal. This demo was a culmination of our prior works and demos: off-roads, on-roads, bidirectional traffic negotiation in single lane roads, and toll-plaza navigation. We have taken up the arduous task of solving the Level-4 autonomous driving by the end of 2024, globally. #machinelearning #deeplearning
Sanjeev Sharma186,204 просмотров • 2 лет назад
Autonomous driving through extremely-tight-dynamic environments with complex, stochastic, and adversarial traffic-dynamics, or simply through an absolute chaos, on sub-urban unstructured roads in India. This kind of traffic and environment has never been attempted in the history of #autonomousdriving. There were no traffic-rules to abide by on this road, other than to perform a left-sided avoidance, if the other obstacles follow the same, else the vehicle will have to change its plan in a stochastic manner, in several of the adversarial multi-agent negotiation settings encountered throughout the autonomous navigation. This demos tested our motion planning and decision making framework to its limits, showcasing its robustness in negotiating such traffic-dynamics with ease. This demo was done on mostly a very narrow road, suited mostly for one-way navigation, but as is customary in India, bidirectional traffic is active on such narrow roads. It can be seen throughout navigation that the incoming vehicles didn't allow any gaps for our #AutonomousVehicles, forcing it to negotiate passively-aggressively its own path through the chaos. Furthermore, obstacles overtaking us didn't follow any rules either, and zig-zagged and moved in crisscross fashion, challenging our motion and behaviour planning software, which negotiated all such scenarios with ease. There were only two points where our vehicle came to halt, when two girls on a two-wheeler didn't stop and just kept on navigating, despite our vehicle being closer to the narrow passage and it having the right of way, and despite a bike being parked over there by someone, making it a very challenging scenario both for the humans and for the decision making autonomous agent(s). This demo was done in the Awadhpuri area, on the Durga Mata road. This framework was last shown in relatively much sparser traffic in our Kankali Kali Mata demo last month. It is being scaled further with deep unsupervised and #reinforcementlearning , and in the coming weeks, it will play a critical role in our endeavour to solving the Level-4 autonomy problem by the end of the year. This kind of traffic negotiation has never been attempted by any autonomous driving company ever. While a 90-degree turn is usually discussed as a corner case in the West, our autonomous vehicle negotiated a blind 90-degree corner, with traffic, with ease. #deeplearning #MachineLearning Swaayatt Robots
Sanjeev Sharma125,218 просмотров • 2 лет назад
Presenting autonomous driving in complex, stochastic and adversarial traffic-dynamics, on the roads in #India. Over the course of last year, we enabled #autonomousdriving in conditions and in situations no one in the autonomous driving industry considered was possible, and in a country like India, where the contemporary belief was that #autonomousvehicles are an impossibility. With the closure of 2023, we present autonomous driving at a very large scale, in the city of Bhopal in India. In this demo our autonomous vehicle at Swaayatt Robots can be seen negotiating the surrounding traffic with ease, where it had to deal with their stochastic and adversarial driving patterns, like suddenly switching lanes and appearing all of a sudden in our vehicle's current driving lane, without adherence to the traffic rules. This demo was a culmination of the cutting-edge research we have been doing, and the technologies we have been developing, over the years, which we showcased throughout in our demos in 2023 -- campus autonomous driving (February), off-roads autonomous driving (April and September), tight-stochastic traffic negotiation (August and September), bidirectional traffic negotiation on a single lane road (October), large-scale city level demo (November), and Toll-Plaza negotiation (December). In 2024, we will scale our technology commercially, and bring it to North America and Europe, to topple this trillion dollar industry, and will also scale our technology throughout India. Wishing everyone a very Happy New Year! #deeplearning #reinforcementlearning #MachineLearning Elon Musk PMO India Narendra Modi Nitin Gadkari DARPA DRDO
Sanjeev Sharma95,416 просмотров • 2 лет назад
Enabling autonomous vehicles perceive their environment using only off-the-shelf cameras has been a long term research objective at Swaayatt Robots. This demo highlights the capabilities of our on-road perception system which is able to detect obstacles, road boundaries, lane markers in images, as well as compute depth of the complex scenes in the environment. The output shown in this video is end-to-end raw output from our deep learning system, without any post processing. The current system, with joint computation of obstacles, lane/road boundaries, and depth, works at 30 FPS on an embedded GPU in our autonomous vehicle, and can achieve higher FPS with further optimization -- which is currently a research in progress. This system is being scaled up for both the day and night operations, and we will showcase its strength towards enabling autonomous driving on a mountainous environment with unpaved roads, in the absence of any delimiters. #deeplearning #autonomousdriving #autonomousvehicles #machinelearning
Sanjeev Sharma18,478 просмотров • 1 год назад
In this demo we extend our prior work on obstacles avoidance at aggressive speeds, showcasing our Thar based autonomous vehicle navigating at near drift speeds, progressing towards our endeavour of Level-5 autonomy. Our autonomous vehicle at Swaayatt Robots was tasked with avoidance of traffic cones on the road, placed in a zig-zag fashion, at aggressive speeds. The location of the marked cones was not known to the planner beforehand. The #autonomousdriving task, i.e., motion planning (time parametrized trajectory computation) and decision making, was made even more challenging by restricting the AI agents to not act on obstacles unless they are within 24m radius. Level-5 #autonomousvehicles should be able to react quickly to overtake, or to avoid, any sudden unforeseeable obstacle or pedestrian on the road to avoid fatalities -- a capability demonstrated by our novel motion planning and decision making algorithmic framework over here. Our previous demo showcased our Bolero based platform consistently keeping speeds beyond 45 KMPH for most part, slowing down to only 39 KMPH at one point. Given Thar has lesser body roll, our framework successfully kept speeds well above 47 KMPH (even at the points of avoidance of obstacles), with speeds reaching as high as 55 KMPH. A typical human driver would feel uncomfortable at speeds beyond 40 KMPH in such as scenario. The entire algorithmic framework with 5 classical (one #reinforcementlearning-) agents , runs at 800+ Hz on a regular i7 processor, single thread. This algorithmic framework is being further scaled up with end-to-end deep reinforcement learning, and will be showcased in the month of March. #deeplearning #machinelearning #motionplanning
Sanjeev Sharma12,811 просмотров • 1 год назад
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 Sharma11,181 просмотров • 1 год назад
Больше нет контента для загрузки