Robots Must Be Ephemeralized | Eric Jang
There is a subfield of robotics research called “sim-to-real” (sim2real) whereby one attempts to solve a robotic task in simulation, and then get a real robot to do the same thing in the real world. My team at Google utilizes Sim2Real techniques extensively in pretty much every domain we study, including locomotion and navigation and manipulation.
There is a subfield of robotics research called “sim-to-real” (sim2real) whereby one attempts to solve a robotic task in simulation, and then get a real robot to do the same thing in the real world. My team at Google utilizes Sim2Real techniques extensively in pretty much every domain we study, including locomotion and navigation and manipulation. The arguments for doing robotic research in simulation are generally well-known in the community: more statistical reproducibility, less concern about safety issues during learning, avoiding the operational complexity of maintaining thousands of…
saved by
related reading
- Science and Engineering for Learned Robotsevjang.com
- Lessons from AI Research Projects: The First 3 Yearsblog.evjang.com
- Software and Hardware for General Robotsblog.evjang.com
- Eric Jang: Robots Must Be Ephemeralizedblog.evjang.com
- Takeaways from DeepMind's RoboCat Paperevjang.com
- How Can We Make Robotics More like Generative Modeling? | Eric Jangevjang.com
- Eric Jangblog.evjang.com
- Stop Simulating, Start Experiencingpaoloai.substack.com
- State of Robot Learning, December 2025vedder.io
- The Final Offshoringfinaloffshoring.com
- The Reality Gap in Roboticsrobotics-reality-gap.github.io
- Building Worlds That Train Robotsworldlabs.ai