Intelligent Robotics group will appear in ICRA 2020 in Paris, with three accepted papers:
- Karol Arndt and his colleagues are going to present a method that allows for data-efficient and safe sim-to-real transfer of reinforcement learning policies through meta-learning (preprint available here);
- Jens Lundell and his colleagues are going to present a method that allows end-to-end top grasp planning methods to generate full six-degree-of-freedom grasps using a single RGB-D view as input (preprint available here);
- Fares Abu-Dakka is going to present a novel and mathematically principled framework for reformulating DMPs using Riemanian metrics, in order to learn and reproduce SPD-matrices-based robot skills.
Congratulations to the authors and see you in Paris!