James Doebbler

Improved Adaptive–Reinforcement Learning Control for Morphing Unmanned Air Vehicles

This paper presents an improved adaptive-reinforcement learning control methodology for the problem of unmanned air vehicle morphing control. The reinforcement learning morphing control function that learns the optimal shape change policy is integrated with an adaptive dynamic inversion control trajectory tracking function. An episodic unsupervised learning simulation using the Q-learning method is developed to replace an earlier and less accurate actor-critic algorithm. Sequential function approximation, a Galerkin-based scattered data approximation scheme, replaces a K-nearest neighbors (KNN) method and is used to generalize the learning from previously experienced quantized states and actions to the continuous state-action space, all of which may not have been experienced before. The improved method showed smaller errors and improved learning of the optimal shape compared to the KNN.

Boom and Receptacle Autonomous Air Refueling Using Visual Snake Optical Sensor

Autonomous air refueling is an important capability for the future deployment of unmanned air vehicles, because it permits unmanned air vehicles to be ferried in flight to overseas theaters of operation instead of being shipped unassembled in containers. This paper demonstrates the feasibility of precise and reliable boom and receptacle autonomous air refueling, without a human operator or supervisor, for nonmicrosized unmanned air vehicles. The system is composed of a vision sensor based on active deformable contour algorithms (visual snakes) and its relative navigation system integrated with a boom controller. The sensor camera is mounted on the tanker aircraft near the boom and images a single passive target image painted near the refueling receptacle on a receiver unmanned air vehicle. Controllers are developed in the paper for the refueling boom, and the stationkeeping controllers of the receiver unmanned air vehicle and tanker aircraft Performance and feasibility of the total system is demonstrated by simulated docking maneuvers in the presence of various levels of turbulence. Results presented in the paper show that the integrated sensor and controller enables precise boom and receptacle air refueling, including consideration.

Boom and Receptacle Autonomous Air Refueling Using a Visual Pressure Snake Optical Sensor

Autonomous in-flight air refueling is an important capability for the future deployment of unmanned air vehicles, since they will likely be ferried in flight to overseas theaters of operation instead of being shipped unassembled in containers. This paper introduces a vision sensor based on active deformable contour algorithms, and a relative navigation system that enables precise and reliable boom and receptacle autonomous air refueling for non micro sized unmanned air vehicles. The sensor is mounted on the tanker aircraft near the boom, and images a single passive target image painted near the refueling receptacle on the receiver aircraft. Controllers are developed for the automatic control of the refueling boom, and for the station keeping controller of the receiver aircraft. The boom controller is integrated with the active deformable contour sensor system, and feasibility of the total system is demonstrated by simulated docking maneuvers in the presence of various levels of turbulence. Results indicate that the integrated sensor and controller enables precise boom and receptacle air refueling, including consideration of realistic measurement errors and disturbances. I. Introduction There are currently two approaches used for air refueling. The probe-and-drogue refueling system is the standard for the United States Navy and the air forces of most other nations. In this method, the tanker trails a hose with a flexible “basket”, called a drogue, at the end. The drogue is aerodynamically stabilized. It is the responsibility of the pilot of the receiver aircraft to maneuver the receiver’s probe into the drogue. This method is used for small, agile aircraft such as fighters because both the hose and drogue are flexible and essentially passive during re-fueling; a human operator is not required on the tanker. 1‐3 Autonomous in-flight refueling using a probe-and-drogue system is basically a docking situation that probably requires 2 cm accuracy in the relative position of the refueling probe (from the receiving aircraft) with respect to the drogue (from the tanker) during the end-game. This specification is based on the geometry of the existing probe and drogue hardware, and the need to ensure that the tip of the probe contacts only the inner sleeve of the receptacle and not the more lightly constructed and easily damaged shroud. 4 The United States Air Force uses the flying boom developed by Boeing. The boom approach is supervised and controlled by a human operator from a station near the rear of the tanker aircraft, who is responsible for “flying” the boom into the refueling port on the receiver aircraft. In this method, the job of the receiver aircraft is to maintain proper refueling position with respect to the tanker, and leave the precision control function to the human operator in the tanker. 2

Aerospace Vehicle Motion Emulation Using Omni - directional Mobile Platform

Testing and validation of flight hardwar e in ground -based facilities can result in significant cost savings and risk reduction. We designed a relative motion emulator for aerospace vehicles using omni -directional mobile bases which provide large 3 degree -of freedom motion , while Stewart platfor ms mounted atop these bases allow superposition of limited 6 degree -of -freedom motion. This paper addresses the design and implementation of the omni -directional mobile base. Each omni -directional base uses a trio of active split offset castor drive modu les to provide smooth, holonomic, precise control of its motion. Three encoders on each castor, three optical mice sensors , and a 3 -axis inertial measurement unit provide full feedback information to a kinematics based control law. We built a one -third scale prototype to demonstrate design feasibility and for use in testing and development of data fusion techniques, control laws, and a dynamics model of the full -scale platform . Results presented in the paper validate the feasibility of the design and the approach. Nomenclature R = distance from center of mass of base to pivot point w r = wheel radius (m) c r = distance from pivot to shaft along 1 ˆ c c � = distance from pivot to castor CM along 1 ˆ c i � = angle between 1 ˆ

Mobile Robotic System for Ground Testing of Multi- Spacecraft Proximity Operations

Ground testing of multi-spacecraft proximity operations with hardware in-the-loop is currently an expensive and challenging process. We present our approach to this problem, applicable to proximity operations of small spacecraft. We are developing a novel autonomous mobile robotic system to emulate full 6 degree of freedom relative motion at high fidelity. An omni-directional robotic base provides unlimited 3-DOF planar motion with moderate precision, while a micron-class hexapod on top provides high precision, limited 6-DOF motion. This multi-vehicle robotic system is designed to accommodate multiple untethered vehicles simultaneously, allowing for the real-time emulation of relative motion for a large variety of multi-spacecraft proximity operations. Compared with other facilities with similar goals, this approach will allow greater freedom of motion at a target operating cost much lower than existing facilities. We believe these capabilities will be invaluable to the growing number of small and micro satellite programs.

Odometry and calibration methods for multi-castor vehicles

We are developing a mobile robot capable of emulating general 6-degree-of-freedom spacecraft relative motion. The omni-directional base uses a trio of active split offset castor drive modules to provide smooth, holonomic, precise control of its motion. Encoders measure the rotations of the six wheels and the three castor pivots. We present a generic odometric algorithm using a least squares framework which is applicable to vehicles with two or more castors and apply it to our unique vehicle configuration. As the accuracy of odometry algorithms depends on the accuracy to which the model parameters are known, a method to perform calibration on the physical robot is needed. We present a geometric calibration method based solely on internal sensor measurements. We present a range of simulation results comparing our odometry results to other algorithms under various systematic and non-systematic errors. We evaluate the ability of our calibration method to accurately determine the true values of our system parameters. The odometry algorithm was also implemented and tested in hardware on our robotic platform. The results presented in the paper validate the calibration and odometry algorithms in both simulation and hardware.

Modeling, Control and Simulation of a Novel Mobile Robotic System

We are developing an autonomous mo- bile robotic system to emulate six degree of freedom relative spacecraft motion during proximity opera- tions. A mobile omni-directional base robot provides x, y, and yaw planar motion with moderate accuracy through six independently driven motors. With a six degree of freedom micro-positioning Stewart platform on top of the moving base, six degree of freedom spacecraft motion can be emulated with high accu- racy. This paper presents our approach to dynamic modeling, control, and simulation for the overall sys- tem. Compared with other simulations that intro- duced significant simplifications, we believe that our rigorous modeling approach is crucial for the high fi- delity hardware in-the-loop emulation.

Human-robot interaction observations from a proto-study using SUAVs for structural inspection

Small unmanned aerial vehicles (SUAVs) have been used for post-disaster structural inspection in the aftermaths of disasters such as Hurricane Katrina and the Berkman Plaza II parking garage collapse [Pratt et al. 2008; Murphy 2006; Murphy et al. 2008]. Video and photos captured from SUAVs provided responders with unique vantage points; unfortunately, interpretation and use of the imagery proved difficult for experts both on- and off-site [Pratt et al. 2008]. This was mostly attributed to spatial data confusion and excess, as inconsistent labeling conventions appeared in post-Katrina missions.

Characterization and Implementation of a Vision-Based 6-DOF Localization System

Testing and validation of flight hardware in ground-based facilities ca n result in significant cost savings and risk reduction. We focus particular attention on ground validation for small satellite proximity operations. We designed a relative motion emulation system for aerospace vehicles using Relative Motion Vehicles (RMVs) capable of large planar motion and limited 6 degree-of-freedom motion. Though the state of the RMV is approximated through internal sensors, an external measurement system is required to correct for secular drift. The commercial NorthStar system from Evolution Robotics provides a vision-based 2-D localization solution using active infrared (IR) beacons. This paper addresses characterization and implementation of the NorthStar system as a 6-DOF state measurement system. The noise characteristics of the NorthStar Detector were determined, as were the output characteristics of the IR light emitting diode (LED) beacons. These characteristics were used to produce a high fidelity model of the measurement system in which multiple Detectors are placed around the perimeter of the workspace and multiple beacons are installed on the RMV. Simulation and hardware test results demonstrate the efficacy of this approac h. Nomenclature

Trajectory Planning for the Cooperative Manipulation of a Flexible Structure by Two Differentially-Driven Robots

In this paper we explore cooperative manipulation of a flexible structure using a team of two nonholonomically-constrained, differentially-driven robots. Cooperative manipulation is achieved by tracking relative trajectories that are designed for both the nonholonomic nature of the platforms and path constraints limiting the deformation of the flexible structure. The relative trajectories are designed by transforming an optimal-trajectory problem to a nonlinear programming problem. A tracking control law is also designed for the nonholonomic nature of the platforms with consideration for the challenges in cooperative manipulation. Results are presented for a simulation example, and a hardware demonstration for a simple case is used to demonstrate the feasibility of the approach.