Whole-body motion planning for manipulation of articulated objects

Burget, Felix; Hornung, Armin; Bennewitz, Maren

doi:10.1109/icra.2013.6630792

Cited by 69 publications

(35 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, the visual servoing algorithm must consider the entire robotic system at once. Burget et al [19] and Dietrich et al [20] both developed methods for considering the entire body during manipulation; however their algorithms deal with pre-planning motions.…”

Section: Problem Statementmentioning

confidence: 99%

A Sensor-Based Dual-Arm Tele-Robotic System

Kruse

Wen

Radke

2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

Abstract-We present a novel system to achieve coordinated task-based control on a dual-arm industrial robot for the general tasks of visual servoing and bimanual hybrid motion/force control. The industrial robot, consisting of a rotating torso and two seven degree-of-freedom arms, performs autonomous visionbased target alignment of both arms with the aid of fiducial markers, two-handed grasping and force control, and robust object manipulation in a tele-robotic framework. The operator uses hand motions to command the desired position for the object via Microsoft Kinect while the autonomous force controller maintains a stable grasp. Gestures detected by the Kinect are also used to dictate different operation modes. We demonstrate the effectiveness of our approach using a variety of common objects with different sizes, shapes, weights, and surface compliances.Note to Practitioners-Industrial robots traditionally are preprogrammed with teach pendants to perform simple repetitive tasks without any sensor feedback. This work was motivated by demonstrating that industrial robots can also perform advanced, sensor-based tasks such as visual servoing, force-feedback control, and tele-operation. Industrial robots are typically limited by the long delay between command and action, but with careful tuning, we show that these sensor-based methods are still feasible even with off-the-shelf sensors.The specific experimental testbed involves a 15 degree-offreedom dual-arm industrial robot with each wrist outfitted with a camera, a rubber contact pad, and a force/torque sensor. A Microsoft Kinect is used to communicate operator commands through gesture. The integrated system involves seven processes running on three computers (2 running Windows 7, 1 running Windows XP) connected through a local hub using the TCP/IP protocol. The communication between the components is based on an object-oriented distributed control and communication software architecture called Robot Raconteur.Though the implementation is for our specific testbed, the approach is sufficiently general to be extended to other robots, end effectors, sensors, and operating systems.

show abstract

Section: Problem Statementmentioning

confidence: 99%

A Sensor-Based Dual-Arm Tele-Robotic System

Kruse

Wen

Radke

2015

IEEE Trans. Automat. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…If this portion extends beyond the current limit task pointỹ, the latter is updated accordingly (Procedure 1, lines 25-28). On termination, control goes back to Algorithm 2, which adds any generated joint motion as an arc (and its final configuration as a node) in T (lines [10][11][12].…”

Section: Constrained Motion Plannermentioning

confidence: 99%

“…This work is supported by the EU FP7 COMANOID project. from task execution [11], [12]; (ii) planning statically stable collision-free trajectories, later converted to dynamically stable motions [13]; (iii) achieve acyclic locomotion and task execution through whole-body contact planning [14].…”

Section: Introductionmentioning

confidence: 99%

Whole-body planning for humanoids along deformable tasks

Cognetti

Fioretti

Oriolo

2016

2016 IEEE International Conference on Robotics and Automation (ICRA)

View full text Add to dashboard Cite

This paper addresses the problem of generating whole-body motions for a humanoid robot that must execute a certain task in an environment containing obstacles. The assigned task trajectory is deformable, and the planner may exploit this feature for finding a solution. Our framework consists of two main components: a constrained motion planner and a deformation mechanism. The basic idea is that the constrained motion planner attempts to solve the problem for the original task. If this proves to be too difficult, the deformation mechanism modifies the task using appropriate heuristic functions. Then, the constrained motion planner is invoked again on the deformed task. If needed, this procedure is iterated. The proposed algorithm has been successfully implemented for the NAO humanoid in V-REP.

show abstract

“…Burget et al [12] developed an approach of whole-body motion planning combining the rapidly-exploring random trees (RRT) with inverse kinematic. Inspired by the RRT-Connect algorithm, a method based on the pseudo-inverse technique was proposed for collision avoidance in [13].…”

Section: Introductionmentioning

confidence: 99%

Coordinated whole-body motion planning for a humanoid robot used on orbit and planetary surface

Zheng

Hu³

2015

2015 IEEE International Conference on Information and Automation

View full text Add to dashboard Cite

To avoid large cost and danger of Extravehicular activity (EVA) and planetary surface exploration, a humanoid robot with high flexibility and mobility is under development. This robot is composed of two 7-DOF (degree of freedom) arms, a 1-DOF waist and two 3-DOF legs. This paper established the kinematics model and addressed whole-body coordinated motion planning methods for the robot, for different application cases: on orbit and planetary surface. For the former, there is no enough gravity (micro-or zero-gravity environment), the dexterity and workspace range are the main factors considered for the whole-body coordination. Combining the position-level and the velocity-level kinematics equations, the common manipulability of the two arms is analyzed, and the best reference workspace is determined. Inspired by the human motion, an appropriate pose (position and attitude) of the target for the two arms are then resolved according to the desired deflection angle of the waist with respect to the initial configuration. When the robot is used on the planetary surface, the gravity is required to be considered for keeping the robot stable during the mission. The coordinated whole motion is planned to adjust the robot's COM (center of mass position) position and make the ZMP (Zero Moment Point) satisfy the balance condition. Finally, the co-simulation model is established in ADAMS/Simulation environment. Simulation results of typical cases verify the proposed methods.

show abstract

Whole-body motion planning for manipulation of articulated objects

Cited by 69 publications

References 26 publications

A Sensor-Based Dual-Arm Tele-Robotic System

A Sensor-Based Dual-Arm Tele-Robotic System

Whole-body planning for humanoids along deformable tasks

Coordinated whole-body motion planning for a humanoid robot used on orbit and planetary surface

Contact Info

Product

Resources

About