Path Planning In Changing Environments Research Articles

A Predictive Path-Following Controller for Continuous Replanning With Dynamic Roadmaps

This letter proposes a predictive path-following controller for efficient time parameterization during continuous replanning with dynamic roadmaps (DRMs). DRMs are an approach for fast global path planning in changing environments and are based on a precomputed graph in the configuration space and mappings from workspace voxels to vertices and edges in the graph. However, DRMs are a kinematic path planner and require subsequent steps of smoothing and trajectory generation before execution. This makes it hard to replan while the robot is moving, it is so because the time parameterization should account for the current position and velocity of the robot. To cope with this issue, a predictive path-following controller is presented, which computes the optimal control actions for moving the robot along the planned paths while respecting the bounds on maximum velocities and accelerations. Furthermore, it enables continuous replanning, i.e., the computation of new paths at fixed intervals, which is particularly useful in combination with a prediction of moving obstacles. The real-time capable approach is evaluated in simulation scenarios with moving obstacles and is experimentally validated for a dual-arm robot with 12 degrees of freedom.

Adaptive Region Boosting method with biased entropy for path planning in changing environment

Path planning in changing environments with difficult regions, such as narrow passages and obstacle boundaries, creates significant challenges. As the obstacles in W-space move frequently, the crowd degree of C-space changes accordingly. Therefore, in order to dynamically improve the sampling quality, it is appreciated for a planner to rapidly approximate the crowd degree of different parts of the C-space, and boost sample densities with them based on their difficulty levels. In this paper, a novel approach called Adaptive Region Boosting (ARB) is proposed to increase the sampling density for difficult areas with different strategies. What's more, a new criterion, called biased entropy, is proposed to evaluate the difficult degree of a region. The new criterion takes into account both temporal and spatial information of a specific C-space region, in order to make a thorough assessment to a local area. Three groups of experiments are conducted based on a dual-manipulator system with 12 DoFs. Experimental results indicate that ARB effectively improves the success rate and outperforms all the other related methods in various dynamical scenarios.