As the proportion of elderly population increases, there is a critical need to develop technology to assist older population in their daily activities. This project aims to explore the use of small aerial and ground co-robots in domestic environment. It is necessary to design co-robots in a way that promotes comfortable interaction with humans and their environment.
The goal of this project is to automate the process of building and infrastructure construction monitoring. The purpose of construction monitoring is to provide construction practitioners—owners, contractors, subcontractors, and tradesmen—with the information they need to easily and quickly make project control decisions.
TERRA-MEPP is a low-cost, autonomous robot that analyzes biofuel crops throughout the growing season. The robot’s sensors collect an unprecedented amount of field data, and high-throughput analytical strategies quickly analyze it to pinpoint plants with desirable yield and sustainability traits.
The goal of this project is to derive algorithms for robotic manipulation and perception of elastic objects that work well and that are easy to implement. The approach taken is control-theoretic and is based on the idea that the shape of an elastic object can be described as the solution to a geometric optimal control problem. This idea leads to representations of object shape that significantly reduce the complexity of algorithms.
The goal of this project is to improve the functional performance of upper-limb prostheses (e.g., prosthetic hands or arms). Surface electromyography (EMG) is used with pattern recognition to enable control. Vibrotactile, electrotactile, and skin stretch feedback are used to restore a sense of proprioception and touch.
The research seeks to develop theoretical underpinnings and practical algorithms for Robust Adaptive Autonomy in Contested Environments for mixed manned-unmanned aerial teams. Unmanned Aircraft (UA) have already seen deployment and success in diverse battle arenas, however, the current heavily-supervised UA operation paradigm is not well matched with the emerging needs of conflict.
Visual systems are needed that can provide detailed descriptions and robust predictions of objects. In some cases, it may be sufficient to name the object. In others, the localization of parts and inference of pose would be desirable. In many others, the object may be unfamiliar, and a rough description should suffice. For example, if an assisted driving program encounters a cow on the road, it should recognize it as a four-legged animal and predict its movement, even if it has not seen a cow before. This project includes the goal to build recognition systems that can recognize everything.
Reinforcement Learning (RL) is a class of machine learning algorithms which addresses the problem of how a behaving agent can learn an optimal behavioral strategy (policy), while interacting with unknown environment. This project studies the use of a distributed Reinforcement Learning (RL) algorithm for multi-agent UAV applications.
A key challenge towards the realization of the concept “using simplicity to control complexity” is to create a Trusted Computing Base (TCB) that promptly acts upon security and safety violations by closely monitoring the behavior of untrustworthy components. This research develops an attack-resilient software architecture for advanced control systems, called “ARSimplex.”
Typically UAVs carry low power-consumption processors with limited memory in order to save weight for maximum payload and flight endurance capabilities. On-board planning algorithms have to be computationally efficient. With this in mind, the projects works toward the development of trajectory generation methods that allows for efficiently generating trajectories for multiple cooperating vehicles.
L1 Adaptive Control is a novel theory for the design of robust adaptive control architectures using fast adaptation schemes. The key feature of L1 adaptive control is the decoupling of the adaptation loop from the control loop, which enables arbitrarily fast adaptation without sacrificing robustness.
This project pursues the design of an embodied, platform- invariant notion of “movement” and execution strategies for a suite of movement platforms, allowing nontechnical users to easily prescribe the behavior of a robot in scenarios like remote bomb disposal and collaborative robots in manufacturing.
Compare Execute Check Engine (C2E2) is a tool for verifying hybrid automata. Hybrid automata are models combining finite state machines and differential equations. They are used for modeling and analyzing robots, autonomous cars, medical devices – more generally, dynamical systems controlled by software.
Distributed or swarm robots are at the frontier of manufacturing, transportation, logistics, and exploration. Programming and managing such systems can be a laborious and error-prone. CyPhyHouse aims to provide application programming interfaces (APIs) and software (compilers, deployers, simulators, debuggers) for reducing above efforts by orders of magnitude.
This project considers the possibility of physically moving wireless network infrastructure to improve/optimize desired performance metrics. For example, we envision WiFi access points on wheels that move within a small region to exploit the multipath nature of wireless signals; drones are envisioned to fly into high demand areas, hovering at strategic locations, and serving as cellular proxies to ground clients. This project is a foray into the landscape of such “robotic wireless networks.”
This project aims to design and build a hybrid robot that can glide, land, and walk. The ground-breaking design connects two widely researched robot forms – UAVs and quadruped robots – and is inspired by the flying squirrel, or Glaucomys volans. This animal can glide between trees and walk on branches to harvest food and escape from predators.