Efficient Planning for Near-Optimal Compliant Manipulation Leveraging Environmental Contact

Charlie Guan1, William Vega-Brown1, Nicholas Roy1

  • 1Massachusetts Institute of Technology



Interactive Session


10:30 - 13:00 | Tue 22 May | podE | TuA@E

Manipulation - Planning 1

Full Text


Path planning classically focuses on avoiding environmental contact. However, some assembly tasks permit contact through compliance, and such contact allows for more efficient and reliable solutions under action uncertainty. But optimal manipulation plans that leverage environmental contact are difficult to compute. Environmental contact produces complex kinematics, that are difficult to plan on. This complexity is usually addressed by discretization over state and action space, but quickly becomes computationally intractable. To overcome these challenges, we use the insight that only actions on configurations near the contact manifold are likely to involve complex kinematics, while segments of the plan through free space do not. Leveraging this structure can greatly reduce the number of states considered and scales much better with problem complexity. We develop an algorithm based on this idea and show that it performs comparably to full MDP solutions at a fraction of the computational cost.

Additional Information

No information added


No videos found


Baxter uses found policy, which uses the edge of opening to reduce uncertainty to accomplish tight assembly task.

  • Tight tolerance assembly tasks is difficult for manipulators with control noise
  • Discretizing continuous optimal control problem into discrete MDP produces successful plans by leveraging environmental contact
  • Full-MDP solutions are slow and scale poorly with problem size
  • We develop the ‘composite MDP’, using contact-likely configurations to more efficiently find solutions while maintaining performance