Tantárgy adatlapja
The goal of this course is to highlight important techniques, methods and results in soft robotics and in deep reinforcement learning-based robot control. The subject of this course will be discussed in weekly consultations on the following topics:
- Standard robotics (configuration space [1]-ch.2, rigid-body motions [1]-ch.3, forward kinematics [1]-ch.4, Jacobian [1]-ch.5, inverse kinematics [1]-ch.6)
- Soft robotics (the physics of soft bodies [3]-ch.13.1, controlling soft robots [3]-ch.13.4, flexible and stretchable electronics and photonics [3]-ch.9)
- Grasping and manipulation [1]-ch.12. (contact kinematics, contact forces and friction, manipulation)
Deep-RL-based control methods [4] (behavior cloning, policy gradient, q-learning, hybrid methods, transfer learning)
Selected litearutre:
[1] K.M. Lynch, F.C. Park, Modern robotics - mechanics, planning and control, 1st ed., Cambridge University Press 2017 [2] M.W. Spong, S. Hutchinson, M. Vidyasagar, Robot modeling and control, 2nd ed., Wiley 2020 [3] The Science of Soft Robots - Design, Materials and Information Processing, Eds. K. Suzumori, K. Fukuda, R. Niiyama, K. Nakajima, Springer 2023 [4] Sergey Levine, Deep Reinforcement Learning course (CS285) online materials (slides, lecture recordings), UC Berkeley, https://rail.eecs.berkeley.edu/deeprlcourse/ List of skills, professional competences: Understanding of robo t constructions and kinematics; Understanding of fundamental aspects of soft robotics; Understanding of key concepts in deep reinforcement learning and its usability to robotic control
