Safe Reinforcement Learning with Model Uncertainty Estimates

by   Björn Lütjens, et al.

Many current autonomous systems are being designed with a strong reliance on black box predictions from deep neural networks (DNNs). However, DNNs tend to be overconfident in predictions on unseen data and can give unpredictable results for far-from-distribution test data. The importance of predictions that are robust to this distributional shift is evident for safety-critical applications, such as collision avoidance around pedestrians. Measures of model uncertainty can be used to identify unseen data, but the state-of-the-art extraction methods such as Bayesian neural networks are mostly intractable to compute. This paper uses MC-Dropout and Bootstrapping to give computationally tractable and parallelizable uncertainty estimates. The methods are embedded in a Safe Reinforcement Learning framework to form uncertainty-aware navigation around pedestrians. The result is a collision avoidance policy that knows what it does not know and cautiously avoids pedestrians that exhibit unseen behavior. The policy is demonstrated in simulation to be more robust to novel observations and take safer actions than an uncertainty-unaware baseline.


page 1

page 3


Fully Bayesian Recurrent Neural Networks for Safe Reinforcement Learning

Reinforcement Learning (RL) has demonstrated state-of-the-art results in...

Conformal Predictive Safety Filter for RL Controllers in Dynamic Environments

The interest in using reinforcement learning (RL) controllers in safety-...

DropConnect Is Effective in Modeling Uncertainty of Bayesian Deep Networks

Deep neural networks (DNNs) have achieved state-of-the-art performances ...

Collision Avoidance in Pedestrian-Rich Environments with Deep Reinforcement Learning

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

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

Robots that navigate among pedestrians use collision avoidance algorithm...

PaRoT: A Practical Framework for Robust Deep Neural Network Training

Deep Neural Networks (DNNs) are finding important applications in safety...

Please sign up or login with your details

Forgot password? Click here to reset