Robotics and Automation Research
Robotics and automation are advancing rapidly due to innovations in sensors, devices, UAVs, networks, optimization, and machine learning, accelerated by corporate and private investment. These systems have enormous potential to reduce drudgery and improve human experience in healthcare, manufacturing, transportation, safety, and a broad range of other applications, building on emerging advances in cloud computing, ensemble learning, big data, open-source software, and industry initiatives in the "Internet of Things", "Smarter Planet", "Industrial Internet" and "Industry 4.0." Recent developments in sequential non-convex optimization, model predictive control, partially observable Markov decision processes, reinforcement learning, and approximate probabilistic inference hold promise for addressing these problems at scale. Cloud Computing can provide access to large datasets and clusters of remote processors to filter, model, optimize, and share data across systems to improve performance over time.
Faculty
Selected Publications
Learning Ambidextrous Robot Grasping Policies
Learning Ambidextrous Robot Grasping Policies. Jeffrey Mahler, Matthew Matl, Vishal Satish, Mike Danielczuk, Bill DeRose, Stephen McKinley, Ken Goldberg. Science Robotics Journal. V4(26). Jan 2019. [.pdf].
- « Previous
- 1
- 2
- 3
Robots and the Return to Collaborative Intelligence (Commentary)
Robots and the Return to Collaborative Intelligence (Commentary). Ken Goldberg. Nature Machine Intelligence Journal. volume 1, pages 2–4. January 2019. [.pdf]