Reference : Combining Deep Gaussian Process and Rule-Based Method for Decision-Making in Self-Dri...
Scientific congresses, symposiums and conference proceedings : Paper published in a book
Engineering, computing & technology : Computer science
http://hdl.handle.net/10993/44377
Combining Deep Gaussian Process and Rule-Based Method for Decision-Making in Self-Driving Simulation with Small Data
English
Fang, W. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Li, H. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Dang, S. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Huang, Hui mailto [University of Luxembourg > > > ; Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Peng, L. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Hsu, L. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
Wen, W. [Center for Automotive Electronics, Shenzhen Institutes of Advanced Technology, CAS, Shenzhen, P.R. China]
5-Mar-2019
2019 15th International Conference on Computational Intelligence and Security (CIS)
IEEE
267-271
Yes
International
978-1-7281-6093-1
15th International Conference on Computational Intelligence and Security (CIS)
13-16 Dec. 2019
IEEE
Macao
China
[en] control engineering computing;decision making;Gaussian processes;learning (artificial intelligence);mobile robots;regression analysis;road vehicles;traffic engineering computing;reinforcement learning methods;self-driving simulation;virtual roads;Torcs simulation engine;regression model;decision-making problem;multiple sensors;artificial intelligence;self-driving vehicle;rule-based method;deep Gaussian process;Decision making;Kernel;Roads;Training data;Brakes;Automobiles;Data models;gaussian process;kernel function;rule-based;decision-making
[en] Self-driving vehicle is a popular and promising field in artificial intelligence. Conventional architecture consists of multiple sensors, which work collaboratively to sense the units on road to yield a precise and safe driving strategy. Besides the precision and safety, the quickness of decision is also a major concern. In order to react quickly, the vehicle need to predict its next possible action, such as acceleration, brake and steering angle, according to its latest few actions and status. In this paper, we treat this decision-making problem as a regression problem and use deep gaussian process to predict its next action. The regression model is trained using simulation data sets and accurately captures the most significant features. Combined with rule-based method, it can be used in Torcs simulation engine to realize successful loop trip on virtual roads. The proposed method outperforms the existing reinforcement learning methods on the performance indicators of time consumption and the size of data volume. It may be useful for real road tests in the future.
http://hdl.handle.net/10993/44377
10.1109/CIS.2019.00063

File(s) associated to this reference

Fulltext file(s):

FileCommentaryVersionSizeAccess
Limited access
Combining Deep Gaussian Process and Rule-Based Method for Decision-Making in Self-Driving Simulation with Small Data.pdfPublisher postprint311.53 kBRequest a copy

Bookmark and Share SFX Query

All documents in ORBilu are protected by a user license.