Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles

Ding，Liuhui1; Li，Dachuan1,3; Liu，Bowen5; Lan，Wenxing5; Bai，Bing1; Hao，Qi1,3; Cao，Weipeng2; Pei，Ke4

10.1109/ISPA-BDCloud-SocialCom-SustainCom52081.2021.00118

2021

978-1-6654-1193-6

19th IEEE International Symposium on Parallel and Distributed Processing with Applications, 11th IEEE International Conference on Big Data and Cloud Computing, 14th IEEE International Conference on Social Computing and Networking and 11th IEEE International Conference on Sustainable Computing and Communications, ISPA/BDCloud/SocialCom/SustainCom 2021

826-835

30 Sept.-3 Oct. 2021

New York City, NY, USA

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 capture 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.

N/a

第一 ; 通讯

英语

EI

20220611605379

Autonomous vehicles ; Backpropagation ; Intelligent vehicle highway systems ; Motion planning ; Object detection ; Three dimensional computer graphics ; Uncertainty analysis

Highway Systems:406.1 ; Highway Transportation:432 ; Ergonomics and Human Factors Engineering:461.4 ; Data Processing and Image Processing:723.2 ; Artificial Intelligence:723.4 ; Computer Applications:723.5 ; Robot Applications:731.6 ; Probability Theory:922.1

2-s2.0-85124150110

Scopus

1.Southern University of Science and Technology,Department of Computer Science and Engineering,Shenzhen,518055,China
2.College of Computer Science and Software Engineering,Shenzhen University,Shenzhen,518060,China
3.Sifakis Research Institute For Trustworthy Autonomous Systems,Shenzhen,518055,China
4.Huawei Technologies Co. Ltd.,Shenzhen,518129,China
5.

Ding，Liuhui,Li，Dachuan,Liu，Bowen,et al. Capture Uncertainties in Deep Neural Networks for Safe Operation of Autonomous Driving Vehicles[C],2021:826-835.