Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles
This work addresses safety challenges in autonomous driving by integrating uncertainty quantification into motion planning, representing an incremental improvement over existing methods.
The paper tackles the problem of uncertainties in DNN-based perception and vehicle motion for autonomous driving by proposing a Bayesian DNN model to quantify uncertainties and an uncertainty-aware motion planning algorithm, validated in CARLA simulations to improve operational safety while maintaining efficiency.
Uncertainties in Deep Neural Network (DNN)-based perception and vehicle's motion pose challenges to the development of safe autonomous driving vehicles. In this paper, we propose a safe motion planning framework featuring the quantification and propagation of DNN-based perception uncertainties and motion uncertainties. Contributions of this work are twofold: (1) A Bayesian Deep Neural network model which detects 3D objects and quantitatively captures the associated aleatoric and epistemic uncertainties of DNNs; (2) An uncertainty-aware motion planning algorithm (PU-RRT) that accounts for uncertainties in object detection and ego-vehicle's motion. The proposed approaches are validated via simulated complex scenarios built in CARLA. Experimental results show that the proposed motion planning scheme can cope with uncertainties of DNN-based perception and vehicle motion, and improve the operational safety of autonomous vehicles while still achieving desirable efficiency.