DeepAI AI Chat
Log In Sign Up

Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning

by   Michael Everett, et al.
Oculus VR, LLC

Robots that navigate among pedestrians use collision avoidance algorithms to enable safe and efficient operation. Recent works present deep reinforcement learning as a framework to model the complex interactions and cooperation. However, they are implemented using key assumptions about other agents' behavior that deviate from reality as the number of agents in the environment increases. This work extends our previous approach to develop an algorithm that learns collision avoidance among a variety of types of dynamic agents without assuming they follow any particular behavior rules. This work also introduces a strategy using LSTM that enables the algorithm to use observations of an arbitrary number of other agents, instead of previous methods that have a fixed observation size. The proposed algorithm outperforms our previous approach in simulation as the number of agents increases, and the algorithm is demonstrated on a fully autonomous robotic vehicle traveling at human walking speed, without the use of a 3D Lidar.


page 1

page 6

page 8


Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning

Collision avoidance algorithms are essential for safe and efficient robo...

CIAO^: MPC-based Safe Motion Planning in Predictable Dynamic Environments

Robots have been operating in dynamic environments and shared workspaces...

Inroads into Autonomous Network Defence using Explained Reinforcement Learning

Computer network defence is a complicated task that has necessitated a h...

On the Effects of Collision Avoidance on Emergent Swarm Behavior

Swarms of autonomous agents, through their decentralized and robust natu...

Safe Reinforcement Learning with Model Uncertainty Estimates

Many current autonomous systems are being designed with a strong relianc...

Code Repositories


ROS package for dynamic obstacle avoidance for ground robots trained with deep RL

view repo