Safety-oriented path planning for articulated robots

Abstract

This work presents an approach to motion planning for robotic manipulators that aims at improving path quality in terms of safety. Safety is explicitly assessed using the quantity called danger field. The measure of safety can easily be embedded into a heuristic function that guides the exploration of the free configuration space. As a result, the resulting path is likely to have substantially higher safety margin when compared to one obtained by regular planning algorithms. To this end, four planning algorithms have been proposed. The first planner is based on volume trees comprised of bubbles of free configuration space, while the remaining ones represent modifications of classical sampling-based algorithms. Several numerical case studies are carried out to validate and compare the performance of the presented algorithms with respect to classical planners. The results indicate significantly lower danger metric for paths obtained by safety-oriented planners even with some decrease in running time.

Cartesian-Space Motion Planning for Autonomous Construction Machines

“…initially, the tree only contains the starting node n 0 . Then, following the approach originally proposed in [6], a random selector is sampled to select between the two possible extension modalities: random and goal-oriented. To this purpose, the value of the parametric threshold "rand th " plays a fundamental role, since it affects the balance between exploration (random expansion) and exploitation (goal-oriented expansion).…”

“…More in depth, we took into account the following planning algorithms: RRT [7], RRT* [5] and SJRRT [6]. Similarly to cart-RRT, the selected state-of-the-art algorithms have been modified to return a failure if the maximum cardinality value (set to 500 nodes) is reached without finding a solution.…”

“…In order to avoid these drawbacks, a possible solution is represented by addressing the motion planning problem directly at the Cartesian-Space level. We here propose "cart-RRT", a Cartesian-Space randomized algorithm that allows the tree to be extended directly towards the goal, as it has been originally proposed in [6]. In cart-RRT edges are computed as linear segments in the Cartesian-Space and the corresponding joint positions profiles are determined using Inverse Kinematics.…”

Safe Path Planning Algorithms for Mobile Robots Based on Probabilistic Foam

“…On the other hand, several strategies that intend to increase the clearance from obstacles along a given path are already planned, such as [ 21 , 24 , 25 , 26 ]. In [ 27 ], the free configuration space exploration is guided by a heuristic function based on a safety measure called Danger Field. In [ 28 ], Quinlan and Khatib proposed a framework to deal with collision-free motion using structures called Elastic Strips that can deform a path known a priori .…”

Bi-objective Motion Planning Approach for Safe Motions: Application to a Collaborative Robot

“…In [13], a safety criterion was included in several motion planning algorithms. It is a simple version of the Kinetostatic danger field [14] which takes into account the overall position of the manipulator with respect to the obstacles.…”