Melnik, Andrew; Lach, Luca Michael; Plappert, Matthias; Korthals, Timo ; Haschke, Robert ; Ritter, Helge: Using Tactile Sensing to Improve the Sample Efficiency and Performance of Deep Deterministic Policy Gradients for Simulated In-Hand Manipulation Tasks. In: Frontiers in Robotics and AI. Jg.8. 2021
Inhalt
- 2.1 Simulator
- 2.2 Touch Simulation
- 2.3 Reinforcement Learning and Training
- 2.4 Task Environments
- 2.4.1 HandManipulateEgg (HME)
- 2.4.2 HandManipulatePenRotate (HMPR)
- 2.4.3 HandManipulateBlock (HMB)
- 2.4.4 HandManipulateBlockRotateXYZ (HMBRXYZ)
- 2.5 Experimental Analysis Techniques
- 3 Results
- 4 Discussion
- 5 Conclusion
- Data Availability Statement
- Author Contributions
- Funding
- Acknowledgments
- References
- Appendix