Abstract- We present a method for securing guided robot motions in terms of human/robot cooperation. For this, we limit the maximum allowable velocity of the robot based on the distance to the human or to the next obstacle and generate the effective velocity using guidance informations provided by the interacting human. Therefore, we fuse the two heterogenous data types of a camera and a force torque sensor. The cameras are used to monitor the robot's workspace applying a difference image method. Given this obstacle information, distances are calculated between the robot and humans or objects in the environment respectively. The distance within each image is determined via an extended difference image method. The distances acquired from each camera are fused to approximate the real robot to object distance within the workspace. This distance regulates the maximum allowable velocity of the robot. The force/torque sensor provides the guidance information, i.e. amount, direction of the force and moment. This information is used to generate the robot's movement taking the maximum allowable velocity into consideration. Index Terms – human/robot cooperation, industrial robot, workspace supervision, difference image method, heterogeonous multisensor fusion, vision, force torque sensor I.

We present an industrial robot system whose workspace is supervised by several stationary cameras detecting obstacles using a difference image method. All robot transfer motions are checked for collision by an image-based method. If any collision is detected, the robot motion path is changed accordingly. The image processing is simple and robust and could be extended to mobile robots for example for services within a household. Experiments prove good performance.

This paper deals with the problem of picking-up deformable linear workpieces such as cables or ropes with an industrial robot. First, we give a motivation and problem definition. Based on a brief conceptual discussion of possible approaches we derive an algorithm for picking-up hanging deformable linear objects using two light barriers as sensor system. For this hardware, a skill-based approach is described and the parameters and major influence factors are discussed. In an experimental study, the feasibility and reliability under diverse conditions are investigated. The algorithm is found to be very reliable, if certain boundary conditions are met. 1

The paper focuses on the problem of point-to-point trajectory planning for flexible redundant robot manipulators (FRM) in joint space. Compared with irredundant flexible manipulators, a FRM possesses additional possibilities during point-to-point trajectory planning due to its kinematics redundancy. A trajectory planning method to minimize vibration and/or executing time of a point-to-point motion is presented for FRM based on Genetic Algorithms (GAs). Kinematics redundancy is integrated into the presented method as planning variables. Quadrinomial and quintic polynomial are used to describe the segments that connect the initial, intermediate, and final points in joint space. The trajectory planning of FRM is formulated as a problem of optimization with constraints. A planar FRM with three flexible links is used in simulation. Case studies show that the method is applicable.

Abstract In current industrial applications without sensor surveillance, the robot workcell needs to be rather static. If the environment of the robot changes in an unplanned manner, e. g. a human enters the workcell and crosses the trajectory, a collision could result. Current research aims at relaxing the separation of robot and human workspaces. We present the first approach that uses multiple 3D depth images for fast collision detection of multiple unknown objects. The depth sensors are placed around the workcell to observe a common surveilled 3D space. The acquired depth images are used to calculate a conservative approximation of all detected obstacles within the surveilled space. Using a robot model and a segment of its future trajectory, these configurations can be checked for collisions with all detected obstacles. If no collision is detected, the minimum distance to any obstacle may be used to limit the maximum velocity. The approach is applicable to a variety of other applications, such as surveillance of tool engines or museum displays.

Abstract. The paper presents a novel approach to parallel motion planning for robot manipulators in 3D workspaces. The approach is based on a randomized parallel search algorithm and focuses on solving the path planning problem for industrial robot arms working in a reasonably cluttered workspace. The path planning system works in the discretized con guration space which needs not to be represented explicitly. The parallel search is conducted by anumber of rule-based sequential search processes, which work to nd a path connecting the initial con guration to the goal via a number of randomly generated subgoal con gurations. Since the planning performs only on-line collision tests with proper proximity information without using pre-computed information, the approach is suitable for planning problems with multirobot or dynamic environments. The implementation has been carried out on the parallel virtual machine (PVM) of a cluster of SUN4 workstations and SGI machines. The experimental results haveshown that the approachworks well for a 6-dof robot arm in a reasonably cluttered environment, and that parallel computation increases the e ciency of motion planning signi cantly. 1

Four different initialization methods for parallel Branch-and-bound algorithms are described and compared with reference to several criteria. A formal analysis of their idle times and efficiency follows. It indicates that the efficiency of three methods depends on the branching factor of the search tree. Furthermore, the fourth method offers the best efficiency of the overall algorithm when a centralized OPEN set is used. Experimental results by a PRAM simulation support these statements.

Abstract – We present a method for quickly determining the minimum distance between multiple known and multiple unkown objects within a camera image. Known objects are objects with known geometry, position, orientation, and configuration. Unkown objects are objects which have to be detected by a vision sensor but with unkown geometry, position, orientation and configuration. The known objects are modeled and expanded in 3D and then projected into a camera image. The camera image is classified into object areas including known and unknown objects and into non-object areas. The distance is conservatively estimated by searching for the largest expansion radius where the projected model does not intersect the object areas classified as unknown in the camera image. The method requires only minimal computation times and can be used for surveillance and safety applications. Index Terms – vision, camera, distance determination, safety, surveillance I.

A practical distributed planning and control system for industrial robots is presented. The hierarchical concept consists of three independent levels. Each level is modularly implemented and supplies an application interface (API) to the next higher level. At the top level, we propose an automatic motion planner. The motion planner is based on a best-first search algorithm and needs no essential off-line computations. At the middle level, we propose a PC-based robot control architecture, which can easily be adapted to any industrial kinematics and application. Based on a client/server-principle, the control unit establishes an open user interface for including application specific programs. At the bottom level, we propose a flexible and modular concept for the integration of the distributed motion control units based on the CAN bus. The concept allows an online adaptation of the control parameters according to the robot's configuration. This implies high accuracy for the path execution and improves the overall system performance Keywords: 1

A practical distributed planning and control system for industrial robots is presented. The hierarchical concept consists of three independent levels. Each level is modularly implemented and supplies an application interface (API) to the next higher level. At the top level, we propose an automatic motion planner. The motion planner is based on a best-first search algorithm and needs no essential off-line computations. At the middle level, we propose a PC-based robot control architecture, which can easily be adapted to any industrial kinematics and application. Based on a client/server-principle, the control unit establishes an open user interface for including application specific programs. At the bottom level, we propose a flexible and modular concept for the integration of the distributed motion control units based on the CAN bus. The concept allows an online adaptation of the control parameters according to the robot's configuration. This implies high accuracy for the path execution...