Human-driven and autonomously driven cars of today act often reactively to the decisions they follow, which could lead uncomfortable, inefficient, sometimes unsafe situations in stop go traffic. This paper proposes methods for probabilistic anticipation motion preceding vehicle control ego vehicle. We construct: 1) a Markov chain predictor based on observed behavior 2) maximum likelihood historical traffic speed at different locations times. Heuristics are proposed combining two predictions...

Optimal pacing of one's effort during a cycling time-trial or even leisurely long bicycle rides can be challenge not only for novice rider but also the experienced. The rider's level fatigue, upcoming elevation changes, and varying wind speed all contribute to problem complexity. This paper formulates strategy as an optimal control with goal finishing in minimum time while considering pedaling force constraints imposed by velocity fatigue. A phenomenological dynamic model fatigue is...

This paper proposes an optimal control approach to power management and pacing in electric bicycle ride with the objective of minimizing travel time. We assume prior knowledge upcoming terrain. Furthermore human pedaling force constraints are estimated by using a phenomenological fatigue dynamics model. Using terrain information, rider's state (SOF), measured velocity, cadence, charge (SOC) battery, solution problem is obtained via three-state dynamic programming (DP) approach. The proposed...

Cooperative driving is a promising technology for reducing traffic jams, limiting CO <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sub> emissions and accidents. With the future mixed traffic, current platooning concept comes to its limitations when human-driven vehicles interfere with platoon between autonomous without negotiation. In this interfering situation, most of them have break down into two platoons, which may ensure safety while...

A new framework for route guidance, as part of a path decision support tool, off-road driving scenarios is presented in this paper. The algorithm accesses information gathered prior to and during mission which are stored layers central map. incorporates priori knowledge the low resolution soil elevation real-time high-resolution from on-board sensors. challenge high computational cost find optimal over large-scale map mitigated by proposed hierarchical planning algorithm. dynamic programming...

This paper presents methods for estimating statistics of travel time in arterial roads by utilizing sparse vehicular probe data. We use a public data feed from transit buses the City San Francisco as an example source. Sparsity and location updates along with frequent stops, at bus stops traffic lights, complicates estimation each link based on single pass. Unlike most previous papers that focus times, we divide into shorter segments, propose two iterative allocating to segment. Inspired...

Simulation platforms play an important role in helping intelligent vehicle research, especially for the research of cooperative driving due to high cost and risk real experiments.In order ease bring more convenience tests, we introduce simulation platform, called CyberTORCS, driving.Details simulator modules including body control, visualization modeling track are presented.Two examples given validate feasibility effectiveness proposed platform.

Simulation platforms play an important role in helping intelligent vehicle research, especially for the research of cooperative driving due to high cost and risk real experiments. In order ease bring more convenience tests, we introduce simulation platform, called CyberTORCS, driving. Details simulator modules including body control, visualization modeling track are presented. Two examples given validate feasibility effectiveness proposed platform.