Get 20M+ Full-Text Papers For Less Than $1.50/day. Start a 14-Day Trial for You or Your Team.

Learn More →

Self-protective motion planning for mobile manipulators in a dynamic door-closing workspace

Self-protective motion planning for mobile manipulators in a dynamic door-closing workspace Many work conditions require manipulators to open cabinet doors and then gain access to the desired workspace. However, after opening, the unlocked doors can easily close, interrupt a task and potentially break the operating end-effectors. This paper aims to address a manipulator's behavior planning problem for responding to a dynamic workspace released by door opening.Design/methodology/approachA dynamic model of the restricted workspace released by an unlocked door is established. As a whole system to treat, the interactions between the workspace and robot are analyzed by using a partially observable Markov decision process. A self-protective policy decision executed as a belief tree is proposed. To respond to the policy, this study has designed three types of actions: stay on guard in the workspace, using an elbow joint to defense the door and linear escape out of the workspace for self-protection by observing collision risk levels to trigger them. Finally, this study proposes self-protective motion controllers based on risk time optimization to act to the planned actions.FindingsThe elbow defense could balance robotic safety and work efficiency by interrupting the end-effector's work and using the elbow joint to prevent the door-closing in an active collision way. Compared with the stay and escape action, the advantage of the elbow defense is having a predictable performance to quick callback the interrupted work after the risk was relieved.Originality/valueThis work provides guidance for the safe operation of a class of robot operations and the upgrade of motion planning. http://www.deepdyve.com/assets/images/DeepDyve-Logo-lg.png Industrial Robot: The International Journal of Robotics Research and Application Emerald Publishing

Self-protective motion planning for mobile manipulators in a dynamic door-closing workspace

Download PDF
9 pages

Loading next page...
 
/lp/emerald-publishing/self-protective-motion-planning-for-mobile-manipulators-in-a-dynamic-mmIFWq8gqv
Publisher
Emerald Publishing
Copyright
© Emerald Publishing Limited
ISSN
0143-991X
DOI
10.1108/ir-02-2021-0025
Publisher site
See Article on Publisher Site

Abstract

Many work conditions require manipulators to open cabinet doors and then gain access to the desired workspace. However, after opening, the unlocked doors can easily close, interrupt a task and potentially break the operating end-effectors. This paper aims to address a manipulator's behavior planning problem for responding to a dynamic workspace released by door opening.Design/methodology/approachA dynamic model of the restricted workspace released by an unlocked door is established. As a whole system to treat, the interactions between the workspace and robot are analyzed by using a partially observable Markov decision process. A self-protective policy decision executed as a belief tree is proposed. To respond to the policy, this study has designed three types of actions: stay on guard in the workspace, using an elbow joint to defense the door and linear escape out of the workspace for self-protection by observing collision risk levels to trigger them. Finally, this study proposes self-protective motion controllers based on risk time optimization to act to the planned actions.FindingsThe elbow defense could balance robotic safety and work efficiency by interrupting the end-effector's work and using the elbow joint to prevent the door-closing in an active collision way. Compared with the stay and escape action, the advantage of the elbow defense is having a predictable performance to quick callback the interrupted work after the risk was relieved.Originality/valueThis work provides guidance for the safe operation of a class of robot operations and the upgrade of motion planning.

Journal

Industrial Robot: The International Journal of Robotics Research and Application – Emerald Publishing

Published: Nov 16, 2021

Keywords: Robot operation; Dynamic workspace; Physical interaction; Mobile manipulator; Self-protective behaviors; Motion planning; Markov decision

References

  • Learning manipulation actions from a few demonstrations
    Abdo, N.; Kretzschmar, H.; Spinello, L.; Stachniss, C.
  • Automated door opening scheme for non-holonomic mobile manipulator
    Adiwahono, A.H.; Chua, Y.; Tee, K.P.; Liu, B.
  • Probabilistically safe motion planning to avoid dynamic obstacles with uncertain motion patterns
    Aoude, G.S.; Luders, B.D.; Joseph, J.M.; Roy, N.; How, J.P.
  • Human-like reflexes for robotic manipulation using leaky integrate-and-fire neurons
    Bauer, C.; Milighetti, G.; Yan, W.; Mikut, R.
  • PR2 robot fetches beer from the refrigerator
  • Multimodal sensing and active continuous closed-loop feedback for achieving reliable manipulation in the outdoor physical world
    Chan, W.P.; Mizohana, H.; Chen, X.; Shiigi, Y.; Yamanoue, Y.; Nagatsuka, M.; Inaba, M.
  • Door-opening control of a service robot using the multifingered robot hand
    Chung, W.; Rhee, C.; Shim, Y.; Lee, H.; Park, S.
  • Integrated task and motion planning in belief space
    Kaelbling, L.P.; Lozano-Pérez, T.
  • Learning force control policies for compliant manipulation
    Kalakrishnan, M.; Righetti, L.; Pastor, P.; Schaal, S.
  • Trajectory generation of a two-wheeled mobile robot in an uncertain environment
    Kim, J.
  • Importance sampling for online planning under uncertainty
    Luo, Y.; Bai, H.; Hsu, D.; Lee, W.S.
  • Visually and force controlled opening and closing of doors by means of a mobile robot arm
    Milighetti, G.; Hoffmann, E.; Fetzner, A.; Kuntze, H.B.
  • Door opening by joining reinforcement learning and intelligent control
    Nemec, B.; Žlajpah, L.; Ude, A.
  • Multimodal trajectory optimization for motion planning
    Osa, T.
  • Passing through open/closed doors: a solution for 3d scanning robots
    Prieto, S.A.; Adán, A.; Vázquez, A.S.; Quintana, B.
  • A generalized framework for opening doors and drawers in kitchen environments
    Rühr, T.; Sturm, J.; Pangercic, D.; Beetz, M.; Cremers, D.
  • Self-protective whole body motion for humanoid robots based on synergy of global reaction and local reflex
    Shimizu, T.; Saegusa, R.; Ikemoto, S.; Ishiguro, H.; Metta, G.
  • Design and implementation of a mobile robot with autonomous door opening ability
    Su, H.-R.; Chen, K.-Y.
  • Probabilistic robotics
    Thrun, S.
  • Intuitive ‘human-on-the-loop’ interface for tele-operating remote mobile manipulator robots
    Valner, R.; Vunder, V.; Zelenak, A.; Pryor, M.; Aabloo, A.; Kruusamäe, K.
  • An intelligent robot for indoor substation inspection
    Wang, C.; Yin, L.; Zhao, Q.; Wang, W.; Li, C.; Luo, B.
  • Research on the shared control technology for robotic wheelchairs based on topological map
    Wang, F.; Liu, Y.; Zhang, Y.; Gao, Y.; Xiao, L.; Wu, C.
  • Collective robot reinforcement learning with distributed asynchronous guided policy search
    Yahya, A.; Li, A.; Kalakrishnan, M.; Chebotar, Y.; Levine, S.