A new motion planning method for robots in static workspaces is presented. This method proceeds in two phases: a learning phase and a query phase. In the learning phase, a probabilistic roadmap is constructed and stored as a graph whose nodes correspond to collision-free configurations and whose edges correspond to feasible paths between these configurations. These paths are computed using a simple and fast local planner. In the query phase, any given start and goal configurations of the robot are connected to two nodes of the roadmap; the roadmap is then searched for a path joining these two nodes. The method is general and easy to implement. It can be applied to virtually any type of holonomic robot. It requires selecting certain parameters (e.g., the duration of the learning phase) whose values depend on the scene, that is the robot and its workspace. But these values turn out to be relatively easy to choose, Increased efficiency can also be achieved by tailoring some components of the method (e.g., the local planner) to the considered robots. In this paper the method is applied to planar articulated robots with many degrees of freedom. Experimental results show that path planning can be done in a fraction of a second on a contemporary workstation (=150 MIPS), after learning for relatively short periods of time (a few dozen seconds)

In this paper a new paradigm for robot motion planning is proposed. We split the motion planning process into two phases: the learning phase and the query phase. In the learning phase we construct a probabilistic roadmap in configuration space. This roadmap is a graph where nodes correspond to randomly chosen configurations in free space and edges correspond to simple collision-free motions between the nodes. These simple motions are computed using a fast local method. The longer we learn, the denser the roadmap becomes and the better it is for motion planning. In the query phase we can use this roadmap to find paths between different pairs of configurations. If a possible path is not found one can always extend the roadmap by learning further. This gives a very flexible scheme in which learning time and success for queries can be balanced. We will demonstrate the power of the paradigm by applying it to various instances of motion planning : free flying planar robots, plan...

This paper presents a novel algorithm for efficiently computing an interferencefree insertion path of a body into a cavity and shows its practical use in the insertability analysis of custom orthopaedic hip implants. The algorithm is designed to handle tightly fit, very complex three-dimensional bodies requiring fine, complex, coupled six-degree of freedom motions in a preferred direction. It provides a practical method for efficiently handling the geometric complexity of tight fit insertions. The algorithm computes an insertion path consisting of small interference-free body motion steps. It formulates local, linearized configuration space constraints derived from the shapes and computes successive motion steps by solving a series of linear optimization problems whose solution corresponds to the maximum allowed displacement in a preferred direction satisfying the constraints. It either finds a successful insertion path or a stuck configuration. We demonstrate the algorithm ...

During the several decades of research, a number of algorithms intended to solve practical motion planning problems have been presented. However, the intractability of the problem makes it difficult to design algorithms capable of solving hard problems, especially when the number of degrees-of-freedom is large. It is necessary to use all available means to extend the domain of practically solvable problem instances. This paper reports results for a parallel implementation of a motion planner based on two-level search algorithm. The planner can solve difficult problems with many degrees-of-freedom within practicable time limits. Furthermore, easier problems can be solved with unprecedented search resolution. 1.

An Obstacle-Based Probabilistic Roadmap Method for Path Planning. (August 1996) Yan Wu, B.E., Xian Jiaotong University; M.E., Xian Jiaotong University Chair of Advisory Committee: Dr. Nancy M. Amato This thesis presents a new obstacle-based probabilistic roadmap method for motion planning for many degree of freedom robots that can be used to obtain high quality roadmaps even when the robot's configuration space is crowded. The main novelty in this approach is that roadmap candidate points are chosen on the constraint surfaces corresponding to obstacles in the workspace. As a consequence, the roadmap is likely to contain difficult paths, such as those traversing long, narrow passages in the robot's configuration space. The approach can be used for both collisionfree path planning and for planning contact tasks. A path planner based on this approach is implemented for planar articulated robots in a two-dimensional workspace with polygonal obstacles. Experimental results with various types of robots and a range of environments show that well connected roadmaps are generated for most environments, even when the number of nodes in the roadmap is small. After the roadmap is built during preprocessing, many difficult path planning operations are carried out in less than a second.

Abstract—This paper reviews the major contributions to the Motion Planning (MP) field throughout a 35-year period, from classic approaches to heuristic algorithms. Due to the NP-Hardness of the MP problem, heuristic methods have outperformed the classic approaches and have gained wide popularity. After surveying around 1400 papers in the field, the amount of existing works for each method is identified and classified. Especially, the history and applications of numerous heuristic methods in MP is investigated. The paper concludes with comparative tables and graphs demonstrating the frequency of each MP method’s application, and so can be used as a guideline for MP researchers. Keywords—Robot motion planning, Heuristic algorithms. I.

Contents 0.1 Introduction. . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 5 0.2 Calibration automatique d'une cam'era . . . . . . . . . . . . . . . . . 6 0.2.1 Introduction th'eorique . . . . . . . . . . . . . . . . . . . . . . 6 0.2.2 R'ealisation . . . . . . . . . . . . . . . . . . . . . . . . . . . . 18 0.2.3 Bilan du calibrage de la cam'era . . . . . . . . . . . . . . . . . 38 0.3 Calibration de deux robots . . . . . . . . . . . . . . . . . . . . . . . . 40 0.3.1 Position du probl`eme . . . . . . . . . . . . . . . . . . . . . . . 40 0.3.2 Principe de l'approche. . . . . . . . . . . . . . . . . . . . . . . 40 0.3.3 Localisation d'un objet. . . . . . . . . . . . . . . . . . . . . . 41 0.3.4 Prise en compte de la r'ealit'e physique . . . . . . . . . . . . . 41 0.4 Syst`eme de commande des deux robots . . . . . . . . . . . . . . . . . 45 0.4.1 Pr'esentation de KALI: . . . . . . . . . . . . . . . . . . . . . . 45 0.4.2 Pr'esentation de VxWorks: . . . . . . . . . .

The problem of goal-directed, collision-free motion in a complex, unpredictable environment can be solved by tightly integrating high-level deliberative planning with low-level reactive control. This thesis presents two such architectures for a nonholonomic mobile robot. To achieve real-time performance, reactive control capabilities have to be fully realized so that the deliberative planner can be simplified. These architectures are enriched with reactive target reaching and obstacle avoidance modules. Their target reaching modules use indirect-mapping Extended Kohonen Map to provide finer and smoother motion control than direct-mapping methods. While one architecture fuses these modules indirectly via command fusion, the other one couples them directly using cooperative Extended Kohonen Maps, enabling the robot to negotiate unforeseen concave obstacles. The planner for both architectures use a slippery cells technique to decompose the free workspace into fewer cells, thus reducing search time. Any two points in the cell can still be traversed by reactive motion.