Recent advances in perception, planning, and control have enabled legged robots to successfully navigate in environments that are mostly known or well-structured and modeled. The DARPA Robotics Challenge (DRC) 2015 showed that in real-world unstructured and uncertain environments robots often lack robustness with regards to locomotion. From one side, this may be due to modeling uncertainties and actuation inaccuracies that affect the control loops. From the other side, both proprioceptive and exteroceptive perception and planning are crucial for detecting foothold and handhold affordances in the environment, and generating agile motions accordingly.
This workshop will provide a platform for researchers from perception, planning, and control in legged robotics to disseminate and exchange ideas, evaluating their advantages and drawbacks. This will include methods for robust control/planning optimization, such as Model Predictive Control, as well as path planning and perception methods for detecting footholds and handholds on challenging surfaces for legged robots including bipeds and quadrupeds. The goal is to show various ways from sensing the environment to finding contacts and planning/controlling the body and limb trajectories for achieving agile and robust locomotion. The aim is to foster collaboration among researchers that are working on legged robots to advance the state of the art in robot locomotion.
This full day workshop consists of a mixture of presentations on topics including sensing, perception, planning, motion generation, and control for various types of legged robots designed to work indoors and outdoors. To stimulate interaction, we also organize a poster session to encourage the participation of young researchers and promote discussion with the speakers and the audience. Moreover we allocate adequate time for questions and discussion to make the workshop as interactive as possible.
Topics of interest
- robust model predictive control
- robust optimization-based control
- whole-body control
- real-robot implementations
- probabilistic approaches to planning under uncertainty
- locomotion and non-gaited locomotion planning
- motion and path planning for high dimensional environments
- contact planning and optimization
- collision avoidance and self-collision avoidance
- reactive behaviors and emergency behavior
- sensing for 3D reconstruction and scene modeling
- proprioceptive and exteroceptive sensing fusion under uncertainty
- localization and mapping for traversability in static or dynamic environments
- environment segmentation and classification
- visual learning for foot placement in rough terrain
- feature extraction and semantic scene understanding and categorization
This proposed workshop is supported by the IEEE RAS Technical Committees on:
1) Algorithms for Planning and Control of Robot Motion [Fabrizio Flacco, Sertac Karaman, Hanna Kurniawati, Lydia Tapia],
2) Whole-Body Control [Federico L. Moro, Luis Sentis, Jaeheung Park],
3) Model-Based Optimization for Robotics [Katja Mombaur, Christopher G. Atkeson, Thomas Buschmann, Kensuke Harada, Abderrahmane Kheddar]
This work is supported by the FP7-ICT-2013-10 WALK- MAN European Commission project, no 611832.