一种采用迭代优化的移动抓取规划方法
|
摘要
提出了一种无需对目标物体进行预建模的迭代优化移动抓取规划方法.该方法通过点云相机在线对目标物体进行立体模型测量和建模,通过深度卷积神经网络对目标点云生成的多个候选抓取位置的抓取成功率进行评价.然后,对机器人底盘和手爪的位置和姿态进行迭代优化,直到抓取目标物体时机器人达到一个最优的位形.再用A*算法规划一条从机器人当前位置到目标位置的运动路径.最后,在路径的基础上,用一种启发式随机路径逼近算法规划手臂的运动,实现边走边抓的效果.本文的深度学习抓取成功率评估算法在康奈尔数据集上取得了83.3%的精确度.所提运动规划算法能得到更平滑、更短且更有利于后续运动的路径.
A mobile grasp planning method based on iterative optimization is proposed, which needn't model the target object in advance. The 3 D model of the target object is measured and modeled online by the point cloud camera, and the deep convolutional neural network is used to evaluate the success probabilities of the alternative grasp locations generated by the target point cloud. The positions and orientations of the robot base and gripper are optimized iteratively until the robot reaches an optimal configuration when grasping the target object. Then A* algorithm is used to plan a path from the robot current position to the target position. Finally, a heuristic random path approaching algorithm is used to plan the arm motion based on the robot path, so that the robot can walk and grasp at the same time. The deep learning based evaluation algorithm of success probabilities of the alternative grasp locations achieves 83.3% accuracy on Cornell data sets. The proposed motion planning algorithm can get a smoother, shorter and more favorable path for subsequent movements.
A mobile grasp planning method based on iterative optimization is proposed, which needn't model the target object in advance. The 3 D model of the target object is measured and modeled online by the point cloud camera, and the deep convolutional neural network is used to evaluate the success probabilities of the alternative grasp locations generated by the target point cloud. The positions and orientations of the robot base and gripper are optimized iteratively until the robot reaches an optimal configuration when grasping the target object. Then A* algorithm is used to plan a path from the robot current position to the target position. Finally, a heuristic random path approaching algorithm is used to plan the arm motion based on the robot path, so that the robot can walk and grasp at the same time. The deep learning based evaluation algorithm of success probabilities of the alternative grasp locations achieves 83.3% accuracy on Cornell data sets. The proposed motion planning algorithm can get a smoother, shorter and more favorable path for subsequent movements.
引文
[1]Beetz M, Stulp F, Esden-Tempski P, et al. Generality and legibility in mobile manipulation[J]. Autonomous Robots, 2010,28(1):21-44.
[2]Petrovskaya A, Ng A Y. Probabilistic mobile manipulation in dynamic environments, with application to opening doors[C]//International Joint Conference on Artificial Intelligence. Freiburg, Germany:Albert-Ludwigs University of Freiburg, 2007:2178-2184.
[3]Stückler J, Schwarz M, Schadler M, et al. NimbRo explorer:Semiautonomous exploration and mobile manipulation in rough terrain[J]. Journal of Field Robotics, 2016, 33(4):411-430.
[4]Meri?li T, Veloso M, Akin H L. Experience guided mobile manipulation planning[C]//AAAI Workshop–Technical Report.Palo Alto, USA:AAAI, 2012:55-60.
[5]Diankov R, Ratliff N, Ferguson D, et al. Bispace planning:Concurrent multi-space exploration[C]//Robotics:Science and Systems IV. 2008. DOI:10.15607/RSS.2008.IV.021.
[6]Burget F, Bennewitz M, Burgard W. BI2RRT*:An efficient sampling-based path planning framework for task-constrained mobile manipulation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE,2016:3714-3721.
[7]Weghe M V, Ferguson D, Srinivasa S S. Randomized path plan ning for redundant manipulators without inverse kinematics[C]//IEEE-RAS International Conference on Humanoid Robots.Piscataway, USA:IEEE, 2007:477-482.
[8]杨唐文,高立宁,阮秋琦,等.移动双臂机械手系统协调操作的视觉伺服技术[J].控制理论与应用,2015,32(1):69-74.Yang T W, Gao L N, Ruan Q Q, et al. Visual servo technology for coordinated manipulation of a mobile dual-arm manipulator system[J]. Control Theory and Applications, 2015, 32(1):69-74.
[9]LaValle S M, Kuffner J J. Rapidly-exploring random trees:Progress and prospects[C]//4th International Workshop on the Algorithmic Foundations of Robotics. Wellesley, USA:A K Peters, 2001:293-308.
[10]Kuffner J J Jr, LaValle S M. RRT-connect:An efficient approach to single-query path planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE,2000:995-1001.
[11]Karaman S, Frazzoli E. Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research,2011, 30(7):846-894.
[12]Gammell J D, Srinivasa S S, Barfoot T D. Batch informed trees(BIT*):Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2015:3067-3074.
[13]Berenson D, Srinivasa S S, Ferguson D, et al. Manipulation planning on constraint manifolds[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE,2009:1383-1390.
[14]Hart P E, Nilsson N J, Raphael B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(2):100-107.
[15]Stentz A. Optimal and efficient path planning for partiallyknown environments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2002:3310-3317.
[16]Masudur Rahman Al-Arif S M, Iftekharul Ferdous A H M, Hassan Nijami S. Comparative study of different path planning algorithms:A water based rescue system[J]. International Journal of Computer Applications, 2012, 39(5):25-29.
[17]Ratliff N, Zucker M, Bagnell J A, et al. CHOMP:Gradient optimization techniques for efficient motion planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2009:4030-4035.
[18]Park C, Pan J, Manocha D. ITOMP:Incremental trajectory optimization for real-time replanning in dynamic environments[C]//22nd International Conference on Automated Planning and Scheduling. Palo Alto, USA:AAAI, 2012:207-215.
[19]Kalakrishnan M, Chitta S, Theodorou E, et al. STOMP:Stochastic trajectory optimization for motion planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2011:4569-4574.
[20]Schulman J, Duan Y, Ho J, et al. Motion planning with sequential convex optimization and convex collision checking[J]. International Journal of Robotics Research, 2014, 33(9):1251-1270.
[21]Geraerts R, Overmars M H. Creating high-quality paths for motion planning[J]. International Journal of Robotics Research,2007, 26(8):845-863.
[22]Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps[J]. International Journal of Robotics Research, 2014,34(4-5):705-724.
[23]Dong G Q, Zhu Z H. Position-based visual servo control of autonomous robotic manipulators[J]. Acta Astronautica, 2015,115:291-302.
[2]Petrovskaya A, Ng A Y. Probabilistic mobile manipulation in dynamic environments, with application to opening doors[C]//International Joint Conference on Artificial Intelligence. Freiburg, Germany:Albert-Ludwigs University of Freiburg, 2007:2178-2184.
[3]Stückler J, Schwarz M, Schadler M, et al. NimbRo explorer:Semiautonomous exploration and mobile manipulation in rough terrain[J]. Journal of Field Robotics, 2016, 33(4):411-430.
[4]Meri?li T, Veloso M, Akin H L. Experience guided mobile manipulation planning[C]//AAAI Workshop–Technical Report.Palo Alto, USA:AAAI, 2012:55-60.
[5]Diankov R, Ratliff N, Ferguson D, et al. Bispace planning:Concurrent multi-space exploration[C]//Robotics:Science and Systems IV. 2008. DOI:10.15607/RSS.2008.IV.021.
[6]Burget F, Bennewitz M, Burgard W. BI2RRT*:An efficient sampling-based path planning framework for task-constrained mobile manipulation[C]//IEEE/RSJ International Conference on Intelligent Robots and Systems. Piscataway, USA:IEEE,2016:3714-3721.
[7]Weghe M V, Ferguson D, Srinivasa S S. Randomized path plan ning for redundant manipulators without inverse kinematics[C]//IEEE-RAS International Conference on Humanoid Robots.Piscataway, USA:IEEE, 2007:477-482.
[8]杨唐文,高立宁,阮秋琦,等.移动双臂机械手系统协调操作的视觉伺服技术[J].控制理论与应用,2015,32(1):69-74.Yang T W, Gao L N, Ruan Q Q, et al. Visual servo technology for coordinated manipulation of a mobile dual-arm manipulator system[J]. Control Theory and Applications, 2015, 32(1):69-74.
[9]LaValle S M, Kuffner J J. Rapidly-exploring random trees:Progress and prospects[C]//4th International Workshop on the Algorithmic Foundations of Robotics. Wellesley, USA:A K Peters, 2001:293-308.
[10]Kuffner J J Jr, LaValle S M. RRT-connect:An efficient approach to single-query path planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE,2000:995-1001.
[11]Karaman S, Frazzoli E. Sampling-based algorithms for optimal motion planning[J]. International Journal of Robotics Research,2011, 30(7):846-894.
[12]Gammell J D, Srinivasa S S, Barfoot T D. Batch informed trees(BIT*):Sampling-based optimal planning via the heuristically guided search of implicit random geometric graphs[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2015:3067-3074.
[13]Berenson D, Srinivasa S S, Ferguson D, et al. Manipulation planning on constraint manifolds[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE,2009:1383-1390.
[14]Hart P E, Nilsson N J, Raphael B. A formal basis for the heuristic determination of minimum cost paths[J]. IEEE Transactions on Systems Science and Cybernetics, 1968, 4(2):100-107.
[15]Stentz A. Optimal and efficient path planning for partiallyknown environments[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2002:3310-3317.
[16]Masudur Rahman Al-Arif S M, Iftekharul Ferdous A H M, Hassan Nijami S. Comparative study of different path planning algorithms:A water based rescue system[J]. International Journal of Computer Applications, 2012, 39(5):25-29.
[17]Ratliff N, Zucker M, Bagnell J A, et al. CHOMP:Gradient optimization techniques for efficient motion planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2009:4030-4035.
[18]Park C, Pan J, Manocha D. ITOMP:Incremental trajectory optimization for real-time replanning in dynamic environments[C]//22nd International Conference on Automated Planning and Scheduling. Palo Alto, USA:AAAI, 2012:207-215.
[19]Kalakrishnan M, Chitta S, Theodorou E, et al. STOMP:Stochastic trajectory optimization for motion planning[C]//IEEE International Conference on Robotics and Automation. Piscataway, USA:IEEE, 2011:4569-4574.
[20]Schulman J, Duan Y, Ho J, et al. Motion planning with sequential convex optimization and convex collision checking[J]. International Journal of Robotics Research, 2014, 33(9):1251-1270.
[21]Geraerts R, Overmars M H. Creating high-quality paths for motion planning[J]. International Journal of Robotics Research,2007, 26(8):845-863.
[22]Lenz I, Lee H, Saxena A. Deep learning for detecting robotic grasps[J]. International Journal of Robotics Research, 2014,34(4-5):705-724.
[23]Dong G Q, Zhu Z H. Position-based visual servo control of autonomous robotic manipulators[J]. Acta Astronautica, 2015,115:291-302.