Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns

Abstract

This paper presents a real-time path planning algorithm that guarantees probabilistic feasibility for autonomous robots with uncertain dynamics operating amidst one or more dynamic obstacles with uncertain motion patterns. Planning safe trajectories under such conditions requires both accurate prediction and proper integration of future obstacle behavior within the planner. Given that available observation data is limited, the motion model must provide generalizable predictions that satisfy dynamic and environmental constraints, a limitation of existing approaches. This work presents a novel solution, named RR-GP, which builds a learned motion pattern model by combining the flexibility of Gaussian processes (GP) with the efficiency of RRT-Reach, a sampling-based reachability computation. Obstacle trajectory GP predictions are conditioned on dynamically feasible paths identified from the reachability analysis, yielding more accurate predictions of future behavior. RR-GP predictions are integrated with a robust path planner, using chance-constrained RRT, to identify probabilistically feasible paths. Theoretical guarantees of probabilistic feasibility are shown for linear systems under Gaussian uncertainty; approximations for nonlinear dynamics and/or non-Gaussian uncertainty are also presented. Simulations demonstrate that, with this planner, an autonomous vehicle can safely navigate a complex environment in realtime while significantly reducing the risk of collisions with dynamic obstacles.

A cable-driven robot for architectural constructions: a visual-guided approach for motion control and path-planning

“…There are several different approaches for planning the path of mobile robot in unknown environments with static and dynamic obstacles (Julia et al 2012), other works determine feasible paths from the reachability analysis and topological constraints (Aoude et al 2013;Bhattacharya et al 2012) and some visual-guided techniques are currently being applied to aerial vehicles (Yu and Beard 2013). In literature the path planning for cable-driven robot followed multiple courses such as: similar algorithms follow the bug-based principles, where a path is calculated in two modes: the robot moves toward the goal on a straight line and when it finds an obstacle, the robot navigates in a near-mode (Lahouar et al 2009).…”

Human-robot co-navigation using anticipatory indicators of human walking motion

“…Gaussian processes for prediction and a probabilistic extension of RRT are used to plan paths for dynamic environments in [15]. The generation of safe paths is critical in dynamic and uncertain environments; [16] provides a reachabilitybased extension of Gaussian processes to better predict human motion, and uses chance-constrained RRT to plan safe paths. In another study [12], researchers developed a grid-based anytime extension of ARA * and demonstrated its effectiveness assuming that predictive information was available regarding dynamic obstacles.…”

Uncertainty-dependent optimal control for robot control considering high-order cost statistics

“…The local deviations problem consists of minimizing (11) or (12) with J as in (15) and constrained to (13) and (14). In Section III, we first explore the risk-sensitive solution solving problem (12).…”

“…We now include a dynamic obstacle with position x o with passive mass-damper dynamics with noise. This is a similar setting to the one considered in [13]. The error state of the system is now given by…”