Loading video...

Video Failed to Load

There was a problem loading this video. This could be due to a temporary network issue or the video might be unavailable.

Scientists have developed a neural network-based planning framework that enables robots to navigate complex environments and mazes autonomously. Learn more in Science Robotics:

Science Magazine

4,446,053 subscribers

25,783 views • 1 year ago •via X (Twitter)

Science & Technology News & Politics

Anya Rossi• Live Now

Private livecam show

5 Comments

Isaac1 year ago

@SciRobotics @ScienceMagazine Nature solved maze navigation millions of years ago - slime molds can find optimal paths through labyrinths using distributed intelligence. Now our robots are finally catching up to what Physarum polycephalum mastered through evolution.

The New Mocha Joe1 year ago

@SciRobotics We're fckd

WhaleX1 year ago

@SciRobotics "Scientists are revolutionizing robotics with neural network-based planning, allowing robots to navigate complex environments autonomously."

Mobile Scanner1 year ago

Scan any documents, convert images into text, PDF files, etc. 👍

Rad Chad1 year ago

@SciRobotics Hasn’t this been done before? The Micromouse competition comes to mind

Related Videos

Scientists have developed SUPER, an autonomous drone that can navigate unknown and cluttered environments safely, which could help future search and rescue efforts. Learn more in Science Robotics:

Scientists have developed SUPER, an autonomous drone that can navigate unknown and cluttered environments safely, which could help future search and rescue efforts. Learn more in Science Robotics:

Science Magazine

46,125 views • 1 year ago

Scientists have designed a framework that enables a humanoid robot face to produce realistic lip-audio synchronization across 12 different languages, including English, Russian, Korean, and Arabic. Learn more in Science Robotics:

Scientists have designed a framework that enables a humanoid robot face to produce realistic lip-audio synchronization across 12 different languages, including English, Russian, Korean, and Arabic. Learn more in Science Robotics:

Science Magazine

29,535 views • 6 months ago

Scientists have developed a rollable robotic structure that is flexible enough to collapse into a compact hub like a tape measure, but also stiff enough to bear heavy loads like 3D printers when extended. Learn more in Science #Robotics:

Scientists have developed a rollable robotic structure that is flexible enough to collapse into a compact hub like a tape measure, but also stiff enough to bear heavy loads like 3D printers when extended. Learn more in Science #Robotics:

Science Robotics

54,780 views • 8 months ago

This is how Amazon delivery bot will ring your doorbell. It is done by leveraging the same loco-manipulation framework that enables humanoid robots to move boxes, developed by Amazon's Frontier AI & Robotics team.

This is how Amazon delivery bot will ring your doorbell. It is done by leveraging the same loco-manipulation framework that enables humanoid robots to move boxes, developed by Amazon's Frontier AI & Robotics team.

The Humanoid Hub

196,178 views • 9 months ago

Motion planning in complex tasks is hard and still done via slow, explicit, traditional planners. We present a generalist Neural Motion Planner -- a single neural network that plans complex dynamic motions quickly and accurately at test time. Building upon our lab's sim2real efforts, the key idea is to create many complex scenes in simulation and then distill classical motion planner trajectories into a single reactive neural network policy. More details in the thread below! 👇 Open-sourced:

Motion planning in complex tasks is hard and still done via slow, explicit, traditional planners. We present a generalist Neural Motion Planner -- a single neural network that plans complex dynamic motions quickly and accurately at test time. Building upon our lab's sim2real efforts, the key idea is to create many complex scenes in simulation and then distill classical motion planner trajectories into a single reactive neural network policy. More details in the thread below! 👇 Open-sourced:

Deepak Pathak

28,642 views • 1 year ago

San Mateo, California–based Generalist showcases their real-time, end-to-end neural network that controls robots at 100Hz for dexterous manipulation tasks. The model handles fine-motor control, bi-manual coordination, tool use, and generalization across arms and environments.

San Mateo, California–based Generalist showcases their real-time, end-to-end neural network that controls robots at 100Hz for dexterous manipulation tasks. The model handles fine-motor control, bi-manual coordination, tool use, and generalization across arms and environments.

The Humanoid Hub

42,524 views • 1 year ago

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

Google DeepMind introduces Gemini Robotics 1.5, enabling robots to perceive, plan, think, use tools, and act on complex tasks. The agentic framework comprises: ⦿ Gemini Robotics-ER 1.5 (VLM): Orchestrates high-level embodied reasoning and planning. ⦿ Gemini Robotics 1.5 (VLA): Converts visuals and instructions provided by ER 1.5 into actions.

The Humanoid Hub

65,928 views • 10 months ago

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Training a Whole-Body Control Foundation Model -- new work from my team at Agility Robotics A neural network for controlling our humanoid robots which is robust to disturbances, can handle heavy objects, and is a powerful platform for learning new whole-body skills learn more in our blog post ->

Chris Paxton

45,068 views • 11 months ago

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

New paper introduces NaVILA, a vision-language-action (VLA) model that integrates high-level visual-language understanding and low-level locomotion control. It enables humanoid or quadruped robots to navigate unseen environments with natural language instructions.

The Humanoid Hub

20,462 views • 1 year ago

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Robots Using Their Feet to Manipulate Objects ETH Zurich researchers have advanced "pedipulation," where legged robots use their feet for manipulation instead of robotic arms. Their new approach trains robots to navigate and manipulate objects while avoiding static and dynamic obstacles. Tested on the ANYmal quadruped, the method enables precise foot control in complex, unseen environments after minimal training in simulation. Will this research open up new possibilities for efficient, obstacle-aware robot manipulation?

Circuit

11,802 views • 1 year ago

Hopfield recall Spiking Neural network now this one is cool isn't it? -open source, link in comment- This is a Spiking Neural Network (SNN) that can learn and recall patterns through Hebbian learning, similar to a Hopfield network but using biologically-inspired spiking dynamics rather than energy-based settling.

Hopfield recall Spiking Neural network now this one is cool isn't it? -open source, link in comment- This is a Spiking Neural Network (SNN) that can learn and recall patterns through Hebbian learning, similar to a Hopfield network but using biologically-inspired spiking dynamics rather than energy-based settling.

echo.hive

31,452 views • 6 months ago

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.

The most frustrating part of imitation learning is collecting huge amounts of teleop data. But why teleop robots when robots can learn by watching us? Introducing Point Policy, a novel framework that enables robots to learn from human videos without any teleop, sim2real, or RL.

Siddhant Haldar

69,056 views • 1 year ago

Using 3D knitting 🧶, scientists have developed soft actuators for extension, contraction, and bending. These motions are useful in applications such as grippers, lifters, and inspection robots like this one 👇 Vanessa Sanchez Wyss Institute Learn more:

Using 3D knitting 🧶, scientists have developed soft actuators for extension, contraction, and bending. These motions are useful in applications such as grippers, lifters, and inspection robots like this one 👇 Vanessa Sanchez Wyss Institute Learn more:

Advanced Portfolio

30,627 views • 3 years ago

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Implemented a visualization for the neural network today. This is a neural network being trained to learn the snake game in a terminal. It's built in Rust using Ratatui More input details in thread

Bones

165,700 views • 2 years ago

Northwestern University researchers developed modular robots using AI that can adapt to damage and navigate unpredictable terrain, according to a new study

Northwestern University researchers developed modular robots using AI that can adapt to damage and navigate unpredictable terrain, according to a new study

Reuters

3,842,282 views • 4 months ago

While Anthropic and OpenAI race on AI Agents/LLMs, Mistral continues expanding its footprint in physical AI. They just released Robostral Navigate (8B VLA model). It shows strong potential in delivery, logistics, manufacturing, and hospitality--for example, enabling humanoid robots to autonomously navigate multiple rooms to hand a glass of water to an employee,all via natural language instructions in complex environments. Powered by just a single RGB camera (no LiDAR or depth sensors), it achieves 76.6% success on R2R-CE (Room-to-Room in Continuous Environments) unseen benchmarks, outperforming multi-sensor systems. Trained purely in simulation, it generalizes across wheeled, legged, and flying robots.

While Anthropic and OpenAI race on AI Agents/LLMs, Mistral continues expanding its footprint in physical AI. They just released Robostral Navigate (8B VLA model). It shows strong potential in delivery, logistics, manufacturing, and hospitality--for example, enabling humanoid robots to autonomously navigate multiple rooms to hand a glass of water to an employee,all via natural language instructions in complex environments. Powered by just a single RGB camera (no LiDAR or depth sensors), it achieves 76.6% success on R2R-CE (Room-to-Room in Continuous Environments) unseen benchmarks, outperforming multi-sensor systems. Trained purely in simulation, it generalizes across wheeled, legged, and flying robots.

CyberRobo

10,957 views • 21 days ago