Shambhavi Singh

Hello! I'm a first year Ph.D. student at the Fluent Robotics Lab, University of Michigan advised by Prof. Christoforos Mavrogiannis. My research focuses on collborative manipuilation using multiple car-like robot pushers, where we're trying to build robust contact-rich manipulation strategies for planar pushing using optimization and learning based methods. I'm always happy to chat about MAPF, pushing mechanics and the large number of ways of using optimization for planning and control, please feel free to send me an email!

Before joining UM, I was a Research Staff with Prof. Howie Choset at the Robotics Institute, at Carnegie Mellon University, where I worked on building computationally efficient planners for Multi Agent Collective Construction, using problem decomposition and hierachical planning.

I have a Masters of Science in Physics and a Bachelors of Engineering in Electrical and Electronics from BITS Pilani. where I worked with Prof. Ashwin KP on developing a 3-R-P-S parallel manipulator, Prof. Sarang Dhongdi on ad-hoc aerial networks for search and rescue operations, and Prof. Rakesh R. Warier on distributed coordination of networked multi-agent systems.

Email  /  Github  /  Google Scholar  /  Linkedin  /  CV

Research

Hierarchical Planning for Long Horizon Multi-agent Collective Construction

We present a hierarchical approach that first finds a sequence of tasks to complete a goal, then identifies ordering constraints between tasks to parallelize for multiple agents, and finally computes collision-free paths for agents.

Hierarchical Propositional Logic Planning for Multi-Agent Collective Construction

We task teams of robots to collectively construct a modular structure composed of blocks. We employ temporal logic to plan at the task-level (robots pick-up and place blocks), then parallelize and find paths for multiple agents (robots move while carrying blocks) to execute the tasks.

Multi-agent Collective Construction using 3D Decomposition

We use Mixed Integer Linear Programming (MILP) to find a multi-robot plan to construct a modular structure composed of cubic blocks. We use a 3D decomposition based method to first find plans that construct smaller substructures, then aggregate the solutions to obtain a complete plan.

Other Projects

These include coursework, side projects and unpublished research work.

Latent Space Optimization for Modular Robot Design

Designing a VAE to structurally encode robot designs (in known environments) such that we can use Bayesian Optimization to converge on well performing robot designs for unseen environments.

Development and control of 3RPS Parallel Manipulator System

Research Project with Dr. Ashwin KP at BITS Pilani, Goa. Modeled the dynamics and control of a 3RPS Parallel Manipulator platform. Developed the robot with three linear actuators and an acrylic base.

A Survey on Efficiency of Multi-Swarm Systems

For a course project on Embedded Systems Design, we review algorithms used in Multi-Swarm Systems, with a focus on Particle Swarm Optimization techniques. In particular, we present a detailed analysis of algorithms for task allocation, communication and grouping for multi-swarm systems.

Density Function Theory Experiments for materials in Semiconductor Devices

Simulating and visualizing properties of Metals (Al, Cu, Ni, Fe and Ag) and Single and Bi-layer Graphene, implemented in Fortran.

Design and source code from Jon Barron's website