Verifying Learning-Based Robotic Navigation Systems

05/26/2022
by   Guy Amir, et al.
67

Deep reinforcement learning (DRL) has become a dominant deep-learning paradigm for various tasks in which complex policies are learned within reactive systems. In parallel, there has recently been significant research on verifying deep neural networks. However, to date, there has been little work demonstrating the use of modern verification tools on real, DRL-controlled systems. In this case-study paper, we attempt to begin bridging this gap, and focus on the important task of mapless robotic navigation – a classic robotics problem, in which a robot, usually controlled by a DRL agent, needs to efficiently and safely navigate through an unknown arena towards a desired target. We demonstrate how modern verification engines can be used for effective model selection, i.e., the process of selecting the best available policy for the robot in question from a pool of candidate policies. Specifically, we use verification to detect and rule out policies that may demonstrate suboptimal behavior, such as collisions and infinite loops. We also apply verification to identify models with overly conservative behavior, thus allowing users to choose superior policies that are better at finding an optimal, shorter path to a target. To validate our work, we conducted extensive experiments on an actual robot, and confirmed that the suboptimal policies detected by our method were indeed flawed. We also compared our verification-driven approach to state-of-the-art gradient attacks, and our results demonstrate that gradient-based methods are inadequate in this setting. Our work is the first to demonstrate the use of DNN verification backends for recognizing suboptimal DRL policies in real-world robots, and for filtering out unwanted policies. We believe that the methods presented in this work can be applied to a large range of application domains that incorporate deep-learning-based agents.

READ FULL TEXT

Authors

page 1

page 3

page 4

page 5

page 6

page 13

page 14

page 15

05/25/2021

Towards Scalable Verification of RL-Driven Systems

Deep neural networks (DNNs) have gained significant popularity in recent...
12/16/2021

Benchmarking Safe Deep Reinforcement Learning in Aquatic Navigation

We propose a novel benchmark environment for Safe Reinforcement Learning...
09/12/2021

Direct Random Search for Fine Tuning of Deep Reinforcement Learning Policies

Researchers have demonstrated that Deep Reinforcement Learning (DRL) is ...
04/24/2019

How You Act Tells a Lot: Privacy-Leakage Attack on Deep Reinforcement Learning

Machine learning has been widely applied to various applications, some o...
01/20/2020

Counter-example Guided Learning of Bounds on Environment Behavior

There is a growing interest in building autonomous systems that interact...
04/24/2019

Neural Logic Reinforcement Learning

Deep reinforcement learning (DRL) has achieved significant breakthroughs...
06/20/2022

Constrained Reinforcement Learning for Robotics via Scenario-Based Programming

Deep reinforcement learning (DRL) has achieved groundbreaking successes ...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.