Robotics and Cyber-Physical Systems

When designing policies or controllers for autonomous embodied systems, factors such as safety and data efficiency become paramount. For both low-level control and high-level planning problems, the standard practice has been to leverage symbolic domain knowledge (e.g., the governing equations of motion for the system, or an automaton representation of the high-level states) to design structured models that have certifiable guarantees, good generalization, or both (\eg, \citet{propel}). An emerging research direction is to automatically learn or discover the structure of the symbolic knowledge (\eg, \citet{xu2018neural}), which can be viewed as an instance of neurosymbolic programming.

Selected Publications

Dantam, Neil T.; Chaudhuri, Swarat; Kavraki, Lydia E.

The Task-Motion Kit: An Open Source, General-Purpose Task and Motion-Planning Framework Journal Article

In: IEEE Robotics Autom. Mag., vol. 25, no. 3, pp. 61–70, 2018.

Links | BibTeX

Wang, Yue; Chaudhuri, Swarat; Kavraki, Lydia E.

Bounded Policy Synthesis for POMDPs with Safe-Reachability Objectives Inproceedings

In: Proceedings of the 17th International Conference on Autonomous Agents and MultiAgent Systems, AAMAS 2018, Stockholm, Sweden, July 10-15, 2018, pp. 238–246, 2018.

Links | BibTeX

Dantam, Neil T.; Kingston, Zachary K.; Chaudhuri, Swarat; Kavraki, Lydia E.

Incremental Task and Motion Planning: A Constraint-Based Approach Inproceedings

In: Robotics: Science and Systems XII, University of Michigan, Ann Arbor, Michigan, USA, June 18 - June 22, 2016, 2016.

Links | BibTeX

Nedunuri, Srinivas; Prabhu, Sailesh; Moll, Mark; Chaudhuri, Swarat; Kavraki, Lydia E.

SMT-based synthesis of integrated task and motion plans from plan outlines Inproceedings

In: 2014 IEEE International Conference on Robotics and Automation, ICRA 2014, Hong Kong, China, May 31 - June 7, 2014, pp. 655–662, 2014.

Links | BibTeX