Interview with Jean Pierre Sleiman, creator of the paper “Versatile multicontact planning and management for legged loco-manipulation”

Image from paper “Versatile multicontact planning and management for legged loco-manipulation“. © American Affiliation for the Development of Science

We had the possibility to interview Jean Pierre Sleiman, creator of the paper “Versatile multicontact planning and management for legged loco-manipulation”, not too long ago revealed in Science Robotics.

What’s the matter of the analysis in your paper?
The analysis matter focuses on creating a model-based planning and management structure that permits legged cell manipulators to sort out various loco-manipulation issues (i.e., manipulation issues inherently involving a locomotion ingredient). Our examine particularly focused duties that will require a number of contact interactions to be solved, fairly than pick-and-place functions. To make sure our method just isn’t restricted to simulation environments, we utilized it to unravel real-world duties with a legged system consisting of the quadrupedal platform ANYmal outfitted with DynaArm, a custom-built 6-DoF robotic arm.

Might you inform us concerning the implications of your analysis and why it’s an fascinating space for examine?
The analysis was pushed by the will to make such robots, particularly legged cell manipulators, able to fixing quite a lot of real-world duties, reminiscent of traversing doorways, opening/closing dishwashers, manipulating valves in an industrial setting, and so forth. An ordinary method would have been to sort out every activity individually and independently by dedicating a considerable quantity of engineering effort to handcraft the specified behaviors:

That is usually achieved by using hard-coded state-machines through which the designer specifies a sequence of sub-goals (e.g., grasp the door deal with, open the door to a desired angle, maintain the door with one of many ft, transfer the arm to the opposite aspect of the door, move by the door whereas closing it, and many others.). Alternatively, a human knowledgeable could display how you can remedy the duty by teleoperating the robotic, recording its movement, and having the robotic study to imitate the recorded conduct.

Nevertheless, this course of may be very gradual, tedious, and liable to engineering design errors. To keep away from this burden for each new activity, the analysis opted for a extra structured method within the type of a single planner that may routinely uncover the mandatory behaviors for a variety of loco-manipulation duties, with out requiring any detailed steerage for any of them.

Might you clarify your methodology?
The important thing perception underlying our methodology was that the entire loco-manipulation duties that we aimed to unravel might be modeled as Activity and Movement Planning (TAMP) issues. TAMP is a well-established framework that has been primarily used to unravel sequential manipulation issues the place the robotic already possesses a set of primitive expertise (e.g., choose object, place object, transfer to object, throw object, and many others.), however nonetheless has to correctly combine them to unravel extra advanced long-horizon duties.

This attitude enabled us to plot a single bi-level optimization formulation that may embody all our duties, and exploit domain-specific information, fairly than task-specific information. By combining this with the well-established strengths of various planning methods (trajectory optimization, knowledgeable graph search, and sampling-based planning), we have been capable of obtain an efficient search technique that solves the optimization drawback.

The primary technical novelty in our work lies within the Offline Multi-Contact Planning Module, depicted in Module B of Determine 1 within the paper. Its total setup might be summarized as follows: Ranging from a user-defined set of robotic end-effectors (e.g., entrance left foot, entrance proper foot, gripper, and many others.) and object affordances (these describe the place the robotic can work together with the item), a discrete state that captures the mix of all contact pairings is launched. Given a begin and aim state (e.g., the robotic ought to find yourself behind the door), the multi-contact planner then solves a single-query drawback by incrementally rising a tree through a bi-level search over possible contact modes collectively with steady robot-object trajectories. The ensuing plan is enhanced with a single long-horizon trajectory optimization over the found contact sequence.

What have been your major findings?
We discovered that our planning framework was capable of quickly uncover advanced multi- contact plans for various loco-manipulation duties, regardless of having offered it with minimal steerage. For instance, for the door-traversal state of affairs, we specify the door affordances (i.e., the deal with, again floor, and entrance floor), and solely present a sparse goal by merely asking the robotic to finish up behind the door. Moreover, we discovered that the generated behaviors are bodily constant and might be reliably executed with an actual legged cell manipulator.

What additional work are you planning on this space?
We see the introduced framework as a stepping stone towards creating a completely autonomous loco-manipulation pipeline. Nevertheless, we see some limitations that we goal to deal with in future work. These limitations are primarily linked to the task-execution part, the place monitoring behaviors generated on the idea of pre-modeled environments is just viable underneath the belief of a fairly correct description, which isn’t all the time simple to outline.

Robustness to modeling mismatches might be vastly improved by complementing our planner with data-driven methods, reminiscent of deep reinforcement studying (DRL). So one fascinating course for future work can be to information the coaching of a strong DRL coverage utilizing dependable knowledgeable demonstrations that may be quickly generated by our loco-manipulation planner to unravel a set of difficult duties with minimal reward-engineering.

Concerning the creator

Jean-Pierre Sleiman obtained the B.E. diploma in mechanical engineering from the American College of Beirut (AUB), Lebanon, in 2016, and the M.S. diploma in automation and management from Politecnico Di Milano, Italy, in 2018. He’s presently a Ph.D. candidate on the Robotic Methods Lab (RSL), ETH Zurich, Switzerland. His present analysis pursuits embrace optimization-based planning and management for legged cell manipulation.