Skip to main content

ICRA'16 WS on "Legged Robot Falling: Fall Detection, Damage Prevention, and Recovery Actions"

Posted in Events

Objectives and Motivation
Research on legged robots has focused mainly on reliable perception, planning, and control methods for completing challenging tasks. The DARPA Robotics Challenge 2015 showed that when the tether is removed, legged robots may inevitable fall over during a task in an unstructured environment; either when they walk on a flat or rough terrain, or when they are cutting a wall with a drill, opening a door, and turning a valve. In a lot of cases if a legged robot falls over, it may end up with a serious damage. If not, the robot in a real world scenario should stand up and complete the task. Being able to detect such a fall, apply the appropriate actions to prevent a big damage both on the robot and the environment around it, and recover if possible, are necessary for a real world application, where legged robots will need to deal with even rougher terrain and more complicated manipulation tasks under significant uncertainty either for static or dynamically changing environments.
This workshop will provide a platform for researchers from all areas in robotics to disseminate and exchange ideas, evaluating their advantages and drawbacks. This will include from the mechanical design and biomechanics to the perception, planning, and whole-body control methods on real robot and simulations for fall detection, damage prevention, and recovery actions in a falling over scenario. The aim is to foster collaboration among researchers that are working on legged robots to advance the very limited state of the art work in this area.
We propose a half-day workshop consisting of a mixture of presentations on topics including design, sensing, perception, planning, biomechanics, and motion generation for various types of legged robots designed to work indoors and outdoors. To stimulate interaction, we will also organize a poster/video session to encourage the participation of young researchers and promote the discussion with the speakers and the audience. Moreover we will allocate adequate time for questions and discussion to make the workshop as interactive as possible.
Workshops as the IROS’15 “The Path to Success: Failures in Real Robots”, the Humanoids “Workshop on Humanoid Soccer Robots”, and the ICRA’15 “Dynamic Locomotion and Balancing of Humanoids: State of the Art and Challenges” were focused more on analyzing the cause of a fall, the fall recovery for toy-robots, and balancing correspondingly. The proposed workshop will focus on the action to follow an inevitable fall after it has been detected. Given that the DRC this year focused on legged locomotion and a large number of falls took place, we believe that such a workshop will attract a large number of participants and promote interaction and collaboration.

Topics of Interest:

  • mechanical design for a falling scenario and soft robotics
  • robotic simulation for falling
  • exteroceptive and proprioceptive perception for fall detection
  • fall planning and recovery
  • damage prevention control
  • collision avoidance and self-collision avoidance
  • reactive behaviors and emergency behaviors
  • biomechanical analysis of human fall detection
  • whole-body control fall/recovery strategies

Support of an IEEE RAS Technical Committee
This proposed workshop is supported by:
1) IEEE RAS Technical Committee on Humanoids Robotics as confirmed as confirmed by the Technical Committee co-chairs Aude Billard, Eiichi Yoshida, and James Kuffner.
2) IEEE RAS Technical Committee on Algorithms for Planning and Control of Robot Motion as confirmed by the Technical Committee co-chairs Fabrizio Flacco, Sertac Karaman, Hanna Kurniawati, and Lydia Tapia.
3) IEEE RAS Technical Committee on Whole-Body Control as confirmed by the Tehnical Committee co-chairs Federico Moro, Luis Sentis, and Jaeheung Park.

This work is supported by the FP7-ICT-2013-10 WALK- MAN European Commission project.

Special thanks to Ambarish Goswami for his priceless help.

No video selected.