Online Learning for Chance-Constrained Observer of Leading Heavy-Duty Vehicle Power Capability

This paper proposes a stochastic observer for estimating power capability of a preceding heavy-duty vehicle, using its speed measurement and road slope information. A chance-constrained optimisation problem is formulated to take into consideration the uncertainties associated with measurement error in the speed and imperfect knowledge of the road slope. An online learning approach is proposed to solve the chance-constrained optimisation problem, which learns probability distribution of the measurements along the travelled distance. The effectiveness of the proposed observer is analysed in two case studies on real road topographies and compared with an existing deterministic leading vehicle observer. The results show that the proposed leading vehicle observer is robust against uncertainties.

Automated summary

This paper proposes a stochastic observer for estimating the power capability of a preceding heavy-duty vehicle, using its speed measurement and road slope information. An online learning approach is used to solve a chance-constrained optimization problem considering uncertainties. The effectiveness of the proposed observer is demonstrated in case studies on real road topographies, showing its robustness against uncertainties.