Saurav Agarwal
Postdoctoral Researcher
GRASP Laboratory, University of Pennsylvania
Contact: SauravAg@seas.upenn.edu
Postdoctoral Researcher
GRASP Laboratory, University of Pennsylvania
Contact: SauravAg@seas.upenn.edu
Research Focus: Coordination and Motion Planning of Robots
Research Interests
My research focuses on developing large-scale decentralized and collaborative intelligent systems that enable robot teams to work cohesively through environmental perception, inter-robot communication of insights, and coordinated actions. By integrating learning-based methods, rigorous theoretical foundations, and practical field deployments, my aim is to introduce new capabilities, improve efficiency and resilience, ensure scalability, and optimize performance for complex tasks.My Ph.D. thesis unifies coverage of point, curve, and area features in environments into a novel generalized coverage framework, formalized as optimization problems on graphs. We used the formalization to design approximation algorithms with provable guarantees and heuristic algorithms for fast large-scale applications, validating them extensively in simulations and experiments. Prior to the Ph.D., my research comprised analyzing and designing mechanisms and parallel robots using optimization techniques. My experience includes using symbolic algebra systems, developing open-source libraries, leading research projects, and mentoring students.
Recent Research
Coverage of Linear Features using Multiple Robots
Wind considerations in computing the energy consumed while traversing
The battery life is modeled as a constraint on the length of the tours
Optimize the tours for the total travel cost of all the robots
The amount of data gathered is significantly lesser than current solutions, thereby reducing the computation required to analyze the environment
Applications include inspection of road networks and power lines
Publications:
S. Agarwal and S. Akella, "Approximation Algorithms for the Single Robot Line Coverage Problem," Algorithmic Foundations of Robotics XIV (WAFR), Oulu, Finland, June 2021. PDF bib
S. Agarwal and S. Akella, "Line coverage with multiple robots," IEEE International Conference on Robotics and Automation (ICRA), Paris, France, May 2020. PDF bib Video
Variable Formation
Development of algorithms to simultaneously compute the optimal assignments and formation parameters for a team of robots from a given initial formation to a variable goal formation.
The shape of goal formation is provided as input
The scale and location parameters for the goal formation is optimized
Optimal assignments of the robots to the goal positions
Sum of squared travel distance is minimized
Guaranteed collision-free trajectories
Robots start simultaneously and reach their goal positions simultaneously
O(n^3) running time complexity