Research Projects

Collaborative Human-Robot Exploration via Implicit Coordination

Collaborative Human-Robot Exploration via Implicit Coordination

This research seeks to enable human-robot collaborative exploration of a-priori unknown enviornments using implicit coordination.

Read more »
Scalable and Adaptive Aerial Robotic Exploration

Scalable and Adaptive Aerial Robotic Exploration

This research project develops mapping and planning methods for multirotors to enable memory-efficient exploration while generating a high-fidelity map of the environment.

Read more »
Assistive Adaptive-Speed Multirotor Teleoperation

Assistive Adaptive-Speed Multirotor Teleoperation

This research project seeks to improve assistance to humans operating multirotors through narrow gaps and tunnels.

Read more »
Autonomous Cave Surveying

Autonomous Cave Surveying

This research program develops a method for cave surveying in complete darkness with an autonomous aerial vehicle equipped with a depth camera for mapping, downward-facing camera for state estimation, and forward and downward lights.

Read more »
Meshlet Primitives for Dense RGB-D SLAM in Dynamic Environments

Meshlet Primitives for Dense RGB-D SLAM in Dynamic Environments

This research develops an efficient method for fitting meshlet primitives to RGB-D data that achieves high geometric fidelity with minimal overlap, such that the spatial density of primitives is significantly reduced compared to surfels.

Read more »
Dynamical Model Learning and Inversion for Aggressive Quadrotor Flight

Dynamical Model Learning and Inversion for Aggressive Quadrotor Flight

This research seeks to design control strategies that enable quadrotors to track aggressive trajectories precisely and accurately in the presence of external disturbances, unmodeled dynamics, and degraded state estimation.

Read more »
RaD-VIO: Rangefinder-aided Downward Visual-Inertial Odometry

RaD-VIO: Rangefinder-aided Downward Visual-Inertial Odometry

In this work we employ the approximation of the ground underneath as being locally planar and utilize this property in concert with onboard inertial sensors for measuring attitude and a single laser beam based rangefinder to provide fast, robust odometry estimates.

Read more »
Distributed Matroid-Constrained Submodular Maximization for Multi-Robot Exploration: Theory and Practice

Distributed Matroid-Constrained Submodular Maximization for Multi-Robot Exploration: Theory and Practice

This research develops a distributed planning approach for multi-robot information gathering and application to robotic exploration.

Read more »
Fast and Agile Vision-Based Flight with Teleoperation and Collision Avoidance on a Multirotor

Fast and Agile Vision-Based Flight with Teleoperation and Collision Avoidance on a Multirotor

This research presents a multirotor architecture capable of aggressive autonomous flight and collision-free teleoperation in unstructured, GPS-denied environments.

Read more »
Variable Resolution Occupancy Mapping using Gaussian Mixture Models

Variable Resolution Occupancy Mapping using Gaussian Mixture Models

This research presents a method of deriving occupancy at varying resolution by sampling from a distribution and raytracing to the camera position.

Read more »
Distributed Submodular Maximization on Partition Matroids for Planning on Large Sensor Networks

Distributed Submodular Maximization on Partition Matroids for Planning on Large Sensor Networks

This research develops an efficient and distributed algorithm for planning for multi-robot sensor coverage.

Read more »
Reactive Collision Avoidance Using Real-Time Local Gaussian Mixture Model Maps

Reactive Collision Avoidance Using Real-Time Local Gaussian Mixture Model Maps

In this work, we propose representing the world as a mixture of Gaussian distributions, which enables us to represent the environment as a compressed and succinct representation. We use the geometric properties of this representation to enable efficient collision checking the robot surroundings.

Read more »
On-Manifold GMM Registration

On-Manifold GMM Registration

This research develops a method to determine position and orientation from successive depth or LiDAR sensor observations. The method represents the sensor observations as approximate continuous belief distributions. The results demonstrate superior results as compared to the state of the art.

Read more »
Online Adaptive Teleoperation Via Motion Primitives for Mobile Robots

Online Adaptive Teleoperation Via Motion Primitives for Mobile Robots

In this work, we present a novel adaptive teleoperation approach that is amenable to mobile systems using motion primitives for long-duration teleoperation, such as exploration using mobile vehicles or walking for humanoid systems.

Read more »
Online planning for human – multi-robot interactive theatrical performance

Online planning for human – multi-robot interactive theatrical performance

This research develops a full system for controlling multi-robot teams online, meaning that plans do not have to be designed prior to operation.

Read more »
Environment Model Adaptation for Mobile Robot Exploration

Environment Model Adaptation for Mobile Robot Exploration

In this research, we develop a method to produce compressed representations of the environment that enable more efficient evaluation of information gain.

Read more »
Fast Monte-Carlo Localization on Aerial Vehicles using Approximate Continuous Belief Representations

Fast Monte-Carlo Localization on Aerial Vehicles using Approximate Continuous Belief Representations

A robot or a team of robots operating in large known environments require accurate knowledge of their exact location in the environment, in order to execute complex tasks. Limited size, weight and power constraints lead to constraints on the on-board computational capacity of aerial robots. This work presents a Monte-Carlo based real-time localization framework capable of running on such robots, enabled by using a compressed representation of the environment point cloud.

Read more »
Efficient Online Multi-robot Exploration via Distributed Sequential Greedy Assignment

Efficient Online Multi-robot Exploration via Distributed Sequential Greedy Assignment

This research describes a distributed planning approach for multi-robot information gathering and application to robotic exploration.

Read more »
Experience-driven Predictive Control with Robust Constraint Satisfaction under Time-Varying State Uncertainty

Experience-driven Predictive Control with Robust Constraint Satisfaction under Time-Varying State Uncertainty

This research develops a controller that efficiently learns vehicle dynamics while at the same time efficiently ensuring that the vehicle satisfies state and input constraints in the presence of state uncertainty.

Read more »
Online Adaptive Teleoperation via Incremental Intent Modeling

Online Adaptive Teleoperation via Incremental Intent Modeling

Adaptive teleoperation with incremental intent modeling.

Read more »
Active Estimation of Mass Properties for Safe Cooperative Lifting

Active Estimation of Mass Properties for Safe Cooperative Lifting

This research presents a method by which a team of aerial robots can lift an unknown object by learning about the mass distribution of the object while it is still on the ground.

Read more »
Experience-Based Models of Surface Proximal Aerial Robot Flight Performance in Wind

Experience-Based Models of Surface Proximal Aerial Robot Flight Performance in Wind

This work presents an experiment-driven aerodynamic disturbance modeling technique that leverages experiences from past flights to construct a predictive model of the exogenous forces acting on an aerial robot.

Read more »
Efficient Multi-Sensor Exploration using Dependent Observations and Conditional Mutual Information

Efficient Multi-Sensor Exploration using Dependent Observations and Conditional Mutual Information

This research develops a method to leverage conditionally dependent sensor observations for multi-modal exploration.

Read more »