Anticipate your surroundings: Predictive collision detection between dynamic obstacles and planned robot trajectories on the GPU

Proactive collision detection enables robots to efficiently execute tasks in shared human-robot-workspaces by avoiding collision-prone situations. Our work connects motion prediction of RGB-D flow algorithms with motion primitive planning via an efficient voxel Swept-Volume-based collision detection. The approach can handle scenarios with varying contents as we use the same techniques to predict single moving objects but also articulated bodies. Our process chain consists of highly parallel GPU algorithms that allow a full 3D representation of planned trajectories and predictions from live pointclouds in high resolution, while still being online capable. We demonstrated our achievements in two scenarios with different motion granularity.

[1]  Richard Bowden,et al.  Scene Particles: Unregularized Particle-Based Scene Flow Estimation , 2014, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  Dieter Fox,et al.  RGB-D flow: Dense 3-D motion estimation using color and depth , 2013, 2013 IEEE International Conference on Robotics and Automation.

[3]  Rüdiger Dillmann,et al.  Proactive avoidance of moving obstacles for a service robot utilizing a behavior-based control , 2010, 2010 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[4]  K. Kosuge,et al.  Motion planning with worker's trajectory prediction for assembly task partner robot , 2012, 2012 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[5]  Geir Hovland,et al.  Collision avoidance with potential fields based on parallel processing of 3D-point cloud data on the GPU , 2014, 2014 IEEE International Conference on Robotics and Automation (ICRA).

[6]  Rüdiger Dillmann,et al.  GPU-based real-time collision detection for motion execution in mobile manipulation planning , 2013, 2013 16th International Conference on Advanced Robotics (ICAR).

[7]  Dinesh Manocha,et al.  FCL: A general purpose library for collision and proximity queries , 2012, 2012 IEEE International Conference on Robotics and Automation.

[8]  Rüdiger Dillmann,et al.  Unified GPU voxel collision detection for mobile manipulation planning , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[9]  Thomas Brox,et al.  Dense Semi-rigid Scene Flow Estimation from RGBD Images , 2014, ECCV.

[10]  Dmitry Berenson,et al.  Human-robot collaborative manipulation planning using early prediction of human motion , 2013, 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[11]  Jörg Stückler,et al.  Efficient Dense Rigid-Body Motion Segmentation and Estimation in RGB-D Video , 2015, International Journal of Computer Vision.

[12]  Gary M. Bone,et al.  Real-time 3D Collision Avoidance Method for Safe Human and Robot Coexistence , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[13]  Maxim Likhachev,et al.  Planning Long Dynamically Feasible Maneuvers for Autonomous Vehicles , 2008, Int. J. Robotics Res..

[14]  Sebastian Klemm,et al.  Mobile Manipulation Planning Optimized for GPGPU Voxel-Collision Detection in High Resolution Live 3D-Maps , 2014, ISR 2014.

[15]  Torsten Kröger,et al.  Distributed Sensing and Prediction of Obstacle Motions for Mobile Robot Motion Planning , 2006, 2006 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[16]  Gonzalo Ferrer,et al.  Proactive kinodynamic planning using the Extended Social Force Model and human motion prediction in urban environments , 2014, 2014 IEEE/RSJ International Conference on Intelligent Robots and Systems.

[17]  Andrew W. Fitzgibbon,et al.  SphereFlow: 6 DoF Scene Flow from RGB-D Pairs , 2014, 2014 IEEE Conference on Computer Vision and Pattern Recognition.