저가 Redundant Manipulator의 최적 경로 생성을 위한 Deep Deterministic Policy Gradient(DDPG) 학습
Learning Optimal Trajectory Generation for Low-Cost Redundant Manipulator using Deep Deterministic Policy Gradient(DDPG)
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
In this paper, we propose an approach resolving inaccuracy of the low-cost redundant manipulator workspace with low encoder and low stiffness. When the manipulators are manufactured with low-cost encoders and low-cost links, the robots can run into workspace inaccuracy issues. Furthermore, trajectory generation based on conventional forward/inverse kinematics without taking into account inaccuracy issues will introduce the risk of end-effector fluctuations. Hence, we propose an optimization for the trajectory generation method based on the DDPG (Deep Deterministic Policy Gradient) algorithm for the low-cost redundant manipulators reaching the target position in Euclidean space. We designed the DDPG algorithm minimizing the distance along with the jacobian condition number. The training environment is selected with an error rate of randomly generated joint spaces in a simulator that implemented real-world physics, the test environment is a real robotic experiment and demonstrated our approach.
Abstract
In this paper, we propose an approach resolving inaccuracy of the low-cost redundant manipulator workspace with low encoder and low stiffness. When the manipulators are manufactured with low-cost encoders and low-cost links, the robots can run into workspace inaccuracy issues. Furthermore, trajectory generation based on conventional forward/inverse kinematics without taking into account inaccuracy issues will introduce the risk of end-effector fluctuations. Hence, we propose an optimization for the trajectory generation method based on the DDPG (Deep Deterministic Policy Gradient) algorithm for the low-cost redundant manipulators reaching the target position in Euclidean space. We designed the DDPG algorithm minimizing the distance along with the jacobian condition number. The training environment is selected with an error rate of randomly generated joint spaces in a simulator that implemented real-world physics, the test environment is a real robotic experiment and demonstrated our approach.
참고문헌 (22)
- Mohammad Mehdi Fateh, "On the Transforming of Control Space by Manipulator Jacobian", International Journal of Control, Automation, and Systems, 6(1), pp.101~108 (2008), 제어·로봇·시스템학회
- D. L. Pieper, "The Kinematics of Manipulators Under Computer Control", pp.1968
- M. A. Ali, "Closed-form inverse kinematic joint solution for humanoid robots", 2010 IEEE, 2010, ~
- 장동열, "음성인식과 딥러닝 기반 객체 인식 기술이 접목된 모바일 매니퓰레이터 통합 시스템", 로봇학회 논문지, 16(3), pp.270~275 (2021), 한국로봇학회[DOI]
- 박동일, "구난 로봇용 양팔 머니퓰레이터 진동 해석 및 설계", 로봇학회 논문지, 11(4), pp.235~241 (2016), 한국로봇학회
- Z. Bingul, "Applying Neural Network to Inverse Kinematic Problem for 6R Robot Manipulator with Offset Wrist", Adaptive and Natural Computing Algorithms, pp.112~115 (2005)[DOI]
- "Planning a minimum time path for robot manipulator using Genetic Algorithm" (1992)[URL]
- Evan Prianto, "Path Planning for Multi-Arm Manipulators Using Deep Reinforcement Learning: Soft Actor–Critic with Hindsight Experience Replay", Sensors, 20(20), pp.5911~ (2020), MDPI AG[DOI]
- 문지윤, "메타강화학습을 이용한 수중로봇 매니퓰레이터 제어", 한국전자통신학회 논문지, 16(1), pp.95~100 (2021), 한국전자통신학회
- Ander Iriondo, "Pick and Place Operations in Logistics Using a Mobile Manipulator Controlled with Deep Reinforcement Learning", Applied Sciences, 9(2), pp.348~ (2019), MDPI AG[DOI]
- M. Duguleana, "Obstacle avoidance of redundant manipulators using neural networks based reinforcement learning", Robotics and Computer-Integrated Manufacturing, 28(2), pp.132~146 (2011)[DOI]
- J. D. Norwood, "A neural network approach to the redundant robot inverse kinematic problem in the presence of obstacles", PhD, pp.1991
- "Continuous control with deep reinforcement learning" (2015)[URL]
- 이종학, "DDPG 알고리즘을 이용한 양팔 매니퓰레이터의 협동작업 경로상의 특이점 회피 경로 계획", 로봇학회 논문지, 16(2), pp.137~146 (2021), 한국로봇학회[DOI]
- J. P. Merlet, "Jacobian, Manipulability, Condition Number, and Accuracy of Parallel Robots", Journal of Mechanical Design, 128(1), pp.199~206 (2005)[DOI]
- M. Tokic, "Adaptive ε-Greedy Exploration in Reinforcement Learning Based on Value Differences", Annual Conference on Artificial Intelligence, pp.203~210 (2010)
- "Playing Atari with Deep Reinforcement Learning" (2013)[URL]
- D. Silver, "Deterministic Policy Gradient Algorithms", 31st International Conference on Machine Learning, 32(1), pp.387~395 (2014)
- C. C. White III, "Markov decision processes", European Journal of Operational Research, 39(1), pp.1~16 (1989)[DOI]
- G. Farnebäck, "Two-frame motion estimation based on polynomial expansion", Scandinavian conference on Image analysis, pp.363~370 (2003)
- F. Dellaert, "Monte Carlo localization for mobile robots", 1999 IEEE International Conference on Robotics and Automation, 2, pp.1322~1328 (1999)
- A. Poroykov, "Modeling ArUco Markers Images for Accuracy Analysis of Their 3D Pose Estimation", 30th International Conference on Computer Graphics and Machine Vision, 2 (2020)