Call for Contributions
Failures are an essential part of every innovation and development process. Scientific research can often be seen as a leap in the dark, where the methods to be used and even the outcomes cannot be known a priori. Despite their importance, failures are often overlooked in the research process and little time is devoted to reasoning and reporting unsuccessful trials. In this workshop we will try to address this oversight by identifying failure cases and addressing their causes in the context of robot grasping and manipulation. The main aim of the workshop will be for participants to:
- Learn from the experience of others, finding explanations for problems encountered in their research, as well as possible solutions.
- Share unsuccessful ideas, hypotheses, and experiments, and gain insights and possible solutions from others working on similar problems.
- Network and join efforts to address common problems or employing one’s know-how to solve another’s persistent failure case.
- Create new research problems, based on the discussions during the workshop, finding the underlying causes and solutions for common failure cases
- Failure “stories”: a description of a failure situation in robot grasping and manipulation that can illustrate a class of problems in this area. (Potential) solutions can be included and supporting media (video) is encouraged.
- Solutions to common failures causes in robot grasping and manipulation (e.g. slippage, collisions with the environment, bad calibration, etc.)
- Benchmarking in manipulation: Quantifying different sources of failure in robot grasping and manipulation
Max 1 page abstract, IEEE style + 1 PowerPoint slide, optional video. Send to: firstname.lastname@example.org
Submission deadline: September 30th 2020
Joao Bimbo, Yale University
Giulia Vezzani, DeepMind
Kensuke Harada, Osaka University
Dimitrios Kanoulas, University College London
Email organizers at email@example.com