The SIMPAR 2016 Workshop on the Grand Challenges in Robotic Simulation led to some amazing discussions. Presenter slides are provided below (with permission granted).
After decades of robotic simulations focusing on modeling the dynamics of manipulators, the past decade has seen the introduction and widespread adoption of quality software libraries for simulating the dynamics and sensors of dextrous robots interacting with semi- realistic virtual environments. These libraries, and the algorithms that make them possible, are poised to be the scaffolding that supports virtual prototyping, robust planning, model predictive control, machine learning, and robot testing for the foreseeable future.
Significant challenges clearly remain until approaches become sufficiently robust, fast, and accurate for the two key tasks of robotic manipulation (including grasping) and locomotion. But what about after those problems are “solved”? We hope to identify the robotic tasks for which successful simulation would have the greatest impact on robotics research and industry. This workshop aimed to discover the grand challenges the simulation research community should tackle.
We aimed to stimulate discussion between the following participants:
- Simulation researchers. We are targeting the ability to model robots performing tasks for up to minutes at a time, which typically limits runtimes to no slower than 1/10 realtime. For dynamics, that context has mostly been limited to multi-rigid bodies, but we also invite researchers in flexible body dynamics, fracture, fluid dynamics, for example, to attend.
- Roboticists who use simulation for virtual testing.
- Roboticists who use simulation to generate data for machine learning methods.
- Roboticists who use simulation for virtual prototyping.
- Samuel Burden (University of Washington)
- Alejandro Castro (Toyota Research Institute)
- Nilanjan Chakraborty (Stony Brook University)
- Erwin Coumans (Google Brain)
- Sean Curtis (Toyota Research Institute)
- Evan Drumwright (Toyota Research Institute) (workshop introduction) (grand challenge)
- Gilwoo Lee (Carnegie Mellon University)
- Ming Lin (University of North Carolina)
- Shin’ichiro Nakaoka (AIST, developer of Choreonoid)
- Dan Negrut (University of Wisconsin)
- Jerry Pratt (Institute for Human and Machine Cognition)
- Alberto Rodgriguez (MIT)
- Andy Ruina (Cornell)
- Dylan Shell (Texas A&M)
- Michael Sherman (Toyota Research Institute)
- Emo Todorov (University of Washington)
- Jeff Trinkle (RPI)