2021/05/14 by Lars Svensson, Lars G. Svensson, Svensson, Lars +2 · 2 citations
Computer Science · Engineering · #Advanced Control Systems Optimization #Artificial intelligence #Automotive engineering #Computer science #Control (management) #Control engineering #Control theory (sociology) #Engineering #Fault Detection and Control Systems #Fusion #Hydraulic and Pneumatic Systems #Motion control #Motion planning #Robot #Traction (geology) #Traction control system #cs.RO #cs.SY #eess.SY
paper · pdf · doi:10.48550/arxiv.2105.06692
published in arXiv (Cornell University) (Cornell University) · 13 pages, 4 figures
arxiv created 2021/05/14 · openalex publication_date 2021/05/14 · arxiv updated 2021/05/17 · openalex created_date 2022/10/01 · openalex updated_date 2026/08/05
Traction adaptive motion planning and control has potential to improve an an\nautomated vehicle's ability to avoid accident in a critical situation. However,\nsuch functionality require an accurate friction estimate for the road ahead of\nthe vehicle that is updated in real time. Current state of the art friction\nestimation techniques include high accuracy local friction estimation in the\npresence of tire slip, as well as rough classification of the road surface\nahead of the vehicle, based on forward looking camera. In this paper we show\nthat neither of these techniques in isolation yield satisfactory behavior when\ndeployed with traction adaptive motion planning and control functionality.\nHowever, fusion of the two provides sufficient accuracy, availability and\nforesight to yield near optimal behavior. To this end, we propose a fusion\nmethod based on heteroscedastic gaussian process regression, and present\ninitial simulation based results.\n