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

Ken Goldberg

Professor

Pieter Abbeel

Joint Faculty, EECS

Selected Publications

Deep Learning Can Significantly Accelerate Grasp-Optimized Motion Planning

Deep Learning Can Significantly Accelerate Grasp-Optimized Motion Planning. Jeffrey Ichnowski, Yahav Avigal, Vishal Satish, Ken Goldberg. Science Robotics Journal. V5(48), 18 Nov 2020. [Paper] [Video].

Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects

Exploratory Grasping: Asymptotically Optimal Algorithms for Grasping Challenging Polyhedral Objects Mike Danielczuk*, Ashwin Balakrishna*, Daniel Brown, Shivin Devgon, Ken Goldberg. Conference on Robot Learning (CoRL), Online MIT, Cambridge, MA, Nov 2020. [Paper] [5min Video] [Website].

Untangling Dense Knots by Learning Task-Relevant Keypoints

Untangling Dense Knots by Learning Task-Relevant Keypoints. Jennifer Grannen*, Priya Sundaresan*, Brijen Thananjeyan, Jeff Ichnowski, Ashwin Balakrishna, Vainavi Viswanath, Michael Laskey, Joseph E. Gonzalez, Ken Goldberg. Conference on Robot Learning (CoRL), Online MIT, Cambridge, MA, Nov 2020. [Paper] [5min Video] [Website]

Simulating Polyculture Farming to Tune Automation Policies for Plant Diversity and Precision Irrigation

Simulating Polyculture Farming to Tune Automation Policies for Plant Diversity and Precision Irrigation. Yahav Avigal, William Wong, Jensen Gao, Kevin Li, Mark Theis, Mark Preston, Grady Pierroz, Fang Shuo Deng, Ken Goldberg. Winner of Best Student Paper Award. 2020 IEEE Conference on Automation Science and Engineering (CASE), Online (Hong Kong) Aug 20-21, 2020. [Paper] [Presentation Video (15 mins)]

ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions

ABC-LMPC: Safe Sample-Based Learning MPC for Stochastic Nonlinear Dynamical Systems with Adjustable Boundary Conditions. Brijen Thananjeyan*, Ashwin Balakrishna*, Ugo Rosolia, Joseph E. Gonzalez, Aaron Ames, Ken Goldberg. Workshop on the Algorithmic Foundations of Robotics (WAFR), Oulu, Finland, July 2021. [paper]

X-RAY: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions

X-RAY: Mechanical Search for an Occluded Object by Minimizing Support of Learned Occupancy Distributions. Michael Danielczuk, Anelia Angelova, Vincent Vanhoucke, Ken Goldberg. IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, October 2020. [paper], [website].

Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor

Deep Imitation Learning of Sequential Fabric Smoothing From an Algorithmic Supervisor. Daniel Seita, Aditya Ganapathi, Ryan Hoque, Minho Hwang, Edward Cen, Ajay Kumar Tanwani, Ashwin Balakrishna, Brijen Thananjeyan, Jeffrey Ichnowski, Nawid Jamali, Kastu Yamane, Soshi Iba, John Canny, Ken Goldberg.IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Las Vegas, NV, USA, October 2020. [paper], [website].

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].

 

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]