Deep Reactive Planning in Dynamic Environments

by   Kei Ota, et al.

The main novelty of the proposed approach is that it allows a robot to learn an end-to-end policy which can adapt to changes in the environment during execution. While goal conditioning of policies has been studied in the RL literature, such approaches are not easily extended to cases where the robot's goal can change during execution. This is something that humans are naturally able to do. However, it is difficult for robots to learn such reflexes (i.e., to naturally respond to dynamic environments), especially when the goal location is not explicitly provided to the robot, and instead needs to be perceived through a vision sensor. In the current work, we present a method that can achieve such behavior by combining traditional kinematic planning, deep learning, and deep reinforcement learning in a synergistic fashion to generalize to arbitrary environments. We demonstrate the proposed approach for several reaching and pick-and-place tasks in simulation, as well as on a real system of a 6-DoF industrial manipulator. A video describing our work could be found <>.


page 1

page 3

page 6


Affordance Learning from Play for Sample-Efficient Policy Learning

Robots operating in human-centered environments should have the ability ...

Learning Navigation Behaviors End to End

A longstanding goal of behavior-based robotics is to solve high-level na...

Learning Kinematic Feasibility for Mobile Manipulation through Deep Reinforcement Learning

Mobile manipulation tasks remain one of the critical challenges for the ...

End-to-end Decentralized Multi-robot Navigation in Unknown Complex Environments via Deep Reinforcement Learning

In this paper, a novel deep reinforcement learning (DRL)-based method is...

Diagnosing and Augmenting Feature Representations in Correctional Inverse Reinforcement Learning

Robots have been increasingly better at doing tasks for humans by learni...

LBGP: Learning Based Goal Planning for Autonomous Following in Front

This paper investigates a hybrid solution which combines deep reinforcem...

Please sign up or login with your details

Forgot password? Click here to reset