Skip to main content

Resultados relacionados

Resultados totales (Incluyendo duplicados): 2
Encontrada(s) 1 página(s)

UPCommons. Portal del coneixement obert de la UPC
Publication Contribución de congreso (ConferenceOutput)

Towards transferring tactile-based continuous force control policies from simulation to robot

  • Lach, Luca Michael
  • Haschke, Robert
  • Tateo, Davide
  • Peters, Jan
  • Ritter, Helge
  • Borràs Sol, Júlia|||0000-0002-1662-2037
  • Torras, Carme|||0000-0002-2933-398X
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that of grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim- to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We therefore present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. An evaluation in which we compare against a baseline and perform an ablation study shows that our approach outperforms the hand-modeled baseline and that our proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google. com/view/rl-force-ctrl, This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch, the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable, the German Research Center for AI (DFKI), and Hessian.AI. Research presented in this paper has been supported by the German Federal Ministry of Education and Research (BMBF) within the collaborative KIARA project (grant no. 13N16274).
Recercat. Dipósit de la Recerca de Catalunya
Publication Contribución de congreso (ConferenceOutput)

Towards transferring tactile-based continuous force control policies from simulation to robot

  • Lach, Luca Michael
  • Haschke, Robert
  • Tateo, Davide
  • Peters, Jan
  • Ritter, Helge
  • Borràs Sol, Júlia
  • Torras, Carme
The advent of tactile sensors in robotics has sparked many ideas on how robots can leverage direct contact measurements of their environment interactions to improve manipulation tasks. An important line of research in this regard is that of grasp force control, which aims to manipulate objects safely by limiting the amount of force exerted on the object. While prior works have either hand-modeled their force controllers, employed model-based approaches, or have not shown sim- to-real transfer, we propose a model-free deep reinforcement learning approach trained in simulation and then transferred to the robot without further fine-tuning. We therefore present a simulation environment that produces realistic normal forces, which we use to train continuous force control policies. An evaluation in which we compare against a baseline and perform an ablation study shows that our approach outperforms the hand-modeled baseline and that our proposed inductive bias and domain randomization facilitate sim-to-real transfer. Code, models, and supplementary videos are available on https://sites.google. com/view/rl-force-ctrl, This work was supported by the European Union’s Horizon 2020 Marie Curie Actions under grant no. 813713 NeuTouch, the Horizon Europe research and innovation program under grant no. 101070600 SoftEnable, the German Research Center for AI (DFKI), and Hessian.AI. Research presented in this paper has been supported by the German Federal Ministry of Education and Research (BMBF) within the collaborative KIARA project (grant no. 13N16274)., Postprint (published version)