Ensemble Bayesian Decision Making with Redundant Deep Perceptual Control Policies
This work addresses the problem of unreliable neural network behavior in safety-critical systems like autonomous driving, offering a novel redundant control approach, though it is incremental as it builds on existing BNN and ensemble techniques.
The paper tackles the challenge of using neural networks for safety-critical control systems by introducing an ensemble of Bayesian Neural Networks (BNNs) that leverages prediction uncertainty and redundancy to improve reliability. The result is a method that successfully performs an agile autonomous driving task even with multiple sensor failures, whereas individual networks crash under unforeseen input noise.
This work presents a novel ensemble of Bayesian Neural Networks (BNNs) for control of safety-critical systems. Decision making for safety-critical systems is challenging due to performance requirements with significant consequences in the event of failure. In practice, failure of such systems can be avoided by introducing redundancies of control. Neural Networks (NNs) are generally not used for safety-critical systems as they can behave in unexpected ways in response to novel inputs. In addition, there may not be any indication as to when they will fail. BNNs have been recognized for their ability to produce not only viable outputs but also provide a measure of uncertainty in these outputs. This work combines the knowledge of prediction uncertainty obtained from BNNs and ensemble control for a redundant control methodology. Our technique is applied to an agile autonomous driving task. Multiple BNNs are trained to control a vehicle in an end-to-end fashion on different sensor inputs provided by the system. We show that an individual network is successful in maneuvering around the track but crashes in the presence of unforeseen input noise. Our proposed ensemble of BNNs shows successful task performance even in the event of multiple sensor failures.