Probably Approximately Correct Vision-Based Planning using Motion Primitives

02/28/2020
by   Sushant Veer, et al.
0

This paper presents a deep reinforcement learning approach for synthesizing vision-based planners that provably generalize to novel environments (i.e., environments unseen during training). We leverage the Probably Approximately Correct (PAC)-Bayes framework to obtain an upper bound on the expected cost of policies across all environments. Minimizing the PAC-Bayes upper bound thus trains policies that are accompanied by a certificate of performance on novel environments. The training pipeline we propose provides strong generalization guarantees for deep neural network policies by (a) obtaining a good prior distribution on the space of policies using Evolutionary Strategies (ES) followed by (b) formulating the PAC-Bayes optimization as an efficiently-solvable parametric convex optimization problem. We demonstrate the efficacy of our approach for producing strong generalization guarantees for learned vision-based motion planners through two simulated examples: (1) an Unmanned Aerial Vehicle (UAV) navigating obstacle fields with an onboard vision sensor, and (2) a dynamic quadrupedal robot traversing rough terrains with proprioceptive and exteroceptive sensors.

READ FULL TEXT

page 1

page 7

research
06/11/2018

PAC-Bayes Control: Synthesizing Controllers that Provably Generalize to Novel Environments

Our goal is to synthesize controllers for robots that provably generaliz...
research
11/16/2021

Stronger Generalization Guarantees for Robot Learning by Combining Generative Models and Real-World Data

We are motivated by the problem of learning policies for robotic systems...
research
11/16/2021

Learning Provably Robust Motion Planners Using Funnel Libraries

This paper presents an approach for learning motion planners that are ac...
research
06/25/2021

Task-Driven Out-of-Distribution Detection with Statistical Guarantees for Robot Learning

Our goal is to perform out-of-distribution (OOD) detection, i.e., to det...
research
08/05/2020

Generalization Guarantees for Multi-Modal Imitation Learning

Control policies from imitation learning can often fail to generalize to...
research
01/20/2022

Sim-to-Lab-to-Real: Safe Reinforcement Learning with Shielding and Generalization Guarantees

Safety is a critical component of autonomous systems and remains a chall...
research
09/28/2021

Interactive Dynamic Walking: Learning Gait Switching Policies with Generalization Guarantees

In this paper, we consider the problem of adapting a dynamically walking...

Please sign up or login with your details

Forgot password? Click here to reset