Showing papers by "Emmanuel G. Collins published in 2016"
TL;DR: A novel method for adaptive NMPC is presented, called Adaptive Sampling Based Model Predictive Control (Adaptive SBMPC), that combines a radial basis function neural network identification algorithm with a nonlinear optimization method based on graph search.
20 citations
01 Jul 2016
TL;DR: The capabilities demonstrated during the US Army Research Laboratory Robotics Collaborative Technology Alliance Capstone Experiment that took place during October 2014 are summarized in this paper, where four capabilities were evaluated as part of distinct Integrated Research Assessments (IRA): Human Robot Interaction Modalities, Semantic Navigation and Perception, Search and Observation of Doorways, and Search and Grasping of Objects in an Indoor Environment Five task-based assessments (TBAs) using various platforms were also conducted during this timeframe.
Abstract: : This report highlights the capabilities demonstrated during the US Army Research Laboratory Robotics Collaborative Technology Alliance Capstone Experiment that took place during October 2014 The report succinctly presents the activities of the event and provides references for further reading on the specifics of those activities Four capabilities were evaluated as part of distinct Integrated Research Assessments (IRA): Human Robot Interaction Modalities, Semantic Navigation and Perception, Search and Observation of Doorways, and Search and Grasping of Objects in an Indoor Environment Five task-based assessments (TBAs) using various platforms were also conducted during this timeframe, which consisted of the following capabilities: Bracing to Reach and Grasp an Object, Detection and Climbing of Stairs, Leaping over a Span, Dynamically Feasible Motion Planning, and Terrain Aware Motion Planning The results from the IRA and TBA events characterized performance and highlighted areas that call for continued and focused efforts in order to enable advancements in intelligence-based capabilities sufficient for the teaming of autonomous systems with Soldiers
5 citations
TL;DR: In this article, the adaptive sampling-based predictive control of flow separation over a NACA-0025 airfoil using micro-jet actuators is presented for a novel approach to nonlinear model predictive control.
Abstract: Boundary-layer separation, a critical phenomenon in the operation of aerodynamic surfaces, limits the performance of compressor and turbine blades, fixed and rotary wings, as well as bluff bodies moving through a fluid. Flow separation leads to increased drag, decreased lift, and unpredictable vibrations due to unsteadiness. On these systems, effective control of separation could provide greater maneuverability and performance, and reduced vibration. Separated flow is a macroscale phenomenon governed by complex flow interactions, but it can be controlled by microscale actuation. Recently, the emergence of closed-loop methods has enhanced robustness. Modern processors enable the use of sophisticated adaptive control methods that achieve separation control with adaptive models. This paper considers control of flow separation over a NACA-0025 airfoil using microjet actuators. Experimental results are presented for a novel approach to nonlinear model predictive control, referred to as adaptive sampling-based ...
5 citations
TL;DR: Using smart glasses such as Google Glass, this work seeks to develop an HR interface that aids in reducing interaction time and distractions during interaction with the robot.
Abstract: In order for humans to safely work alongside robots in the field, the human-robot (HR) interface, which enables bi-directional communication between human and robot, should be able to quickly and concisely express the robot's intentions and needs. While the robot operates mostly in autonomous mode, the human should be able to intervene to effectively guide the robot in complex, risky and/or highly uncertain scenarios. Using smart glasses such as Google Glass∗, we seek to develop an HR interface that aids in reducing interaction time and distractions during interaction with the robot.