Joseph J. Kehoe

Waypoint navigation for a micro air vehicle using vision-based attitude estimation

Missions envisioned for micro air vehicles may require a high degree of autonomy to operate in unknown environments. As such, vision is a critical technology for mission capability. This paper discusses an autopilot that uses vision coupled with GPS and altitude sensors for waypoint navigation. The vision processing analyses a horizon to estimate roll and pitch information. The GPS and altitude sensors then command values to roll and pitch for navigation between waypoints. A flight test of a MAV using this autopilot demonstrates the resulting closed-loop system is able to autonomously reach several waypoints. The vehicle actually uses a telemetry link to a ground station on which all vision processing and related guidance and control is performed. Several issues, such as estimating heading to account for slow updates, are investigated to increase performance.

Partial aircraft state estimation from optical flow using non-model-based optimization

Computer vision is an enabling technology for autonomous micro aerial vehicle (MAV) applications. This paper presents an approach for the estimation of aircraft angular rates and wind-axis angles using monocular vision. The solution is obtained through nonlinear optimization techniques applied to the optical flow of tracked feature points in the image. The coupled equations of motion for an aircraft and image-based features are developed and utilized to establish a mathematical framework for the estimation process. The technique is then demonstrated in simulation

Vision-based navigation using multi-rate feedback from optic flow and scene reconstruction

Vision-based control is being aggressively pursued for autonomous systems. Such control is particularly valuable for path planning to achieve mission objectives like target tracking and obstacle avoidance. This paper presents a multi-rate strategy that utilises a fast-rate optic flow approach and a slow-rate scene reconstruction approach. The vehicle uses scene reconstruction to generate an accurate map for path planning; however, optic flow is used to avoid obstacles while the scene reconstruction is computed. A switch element is used in the feedback path to determine whether information relating to the reconstructed map or the optical flow should be used for navigation. The resulting controller is able to generate flight trajectories and perform obstacle avoidance within a computational cost which is reasonable given performance demands and computational resources on a wide range of aircraft. A simulation demonstrates the performance of an aircraft that uses the multi-rate controller to avoid an obstacle which is only observed after a turn. Essentially, the fast-rate optic flow indicates the presence of the obstacle during the time that slow-rate scene reconstruction is being performed. The resulting flight path is able to follow mission objectives and avoid a collision.

A Time-Varying Hybrid Model for Dynamic Motion Planning of an Unmanned Air Vehicle

Future unmanned aerial vehicle (UAV) missions are likely to include those for which the characteristic dimensions of the environment are similar in scale to the characteristic dimensions of the vehicle dynamics. This class of missions will require precision trajectory planning and tracking that utilizes the full agility of the vehicle to ensure safety and performance. Hybrid models consisting of a set motion primitives allow for the safe integration of aggressive maneuvers into a motion plan; however, planning precision is limited by the finite set of primitives. This paper presents an extension of existing hybrid modeling strategies to allow for a variable set of motion primitives that are tailored to the current mission-performance requirements. A randomized sampling-based planning approach is then adopted to plan trajectories using this modeling strategy. Performance of the resulting trajectory-planning system is demonstrated through a simulated example.

Path-Parameterization Approach Using Trajectory Primitives for Three-Dimensional Motion Planning

Motion planning determines trajectories for vehicles that link an initial location and heading with a final location and heading. Techniques for motion planning have been developed for two-dimensional maneuvering; however, they are less mature for three-dimensional maneuvering. The concept of motion primitives is particularly attractive for motion planning that determines trajectories as a set of maneuvers that satisfy differential constraints. This paper furthers work on a higher-level abstraction of trajectory primitives that consider sequences of motion primitives. In this paper, trajectory primitives are developed that deal with airspace constraints of an environment. The motion planning is shown to be an optimization involving a pair of trajectory primitives that is related by an intermediate waypoint. The resulting path is completely parameterized by the waypoint location.

SLAM for Flight through Urban Environments using Dimensionality Reduction

Robotic mapping is an enabling technology for the navigation of autonomous vehicles. The problem of estimating both a vehicle’s state and a map of its environment is referred to as Simultaneous Localization and Mapping (SLAM). This paper presents a SLAM framework suitable of a Micro Air Vehicle (MAV) equipped only with a monocular camera. Structure from Motion (SFM) is employed to infer three-dimensional environment information from a stream of digital images. A dimensionality reduction step generates a geometric model of the vehicle’s surroundings by exploiting the structure inherent in urban settings. The focus of this paper is to formulate a vision-only SLAM framework for building maps that are amenable to motion planning algorithms to enable autonomous navigation. Simulation results are presented to demonstrate the SLAM algorithm.

Vision-Based Navigation Using Multi-Rate Feedback from Optic Flow and Scene Reconstruction

of Thesis Presented to the Graduate School of the University of Florida in Partial Fulfillment of the Requirements for the Degree of Master of Science VISION-BASED NAVIGATION USING MULTI-RATE FEEDBACK FROM OPTIC FLOW AND SCENE RECONSTRUCTION By Amanda Arvai December 2005 Chair: Richard C. Lind, Jr. Major Department: Mechanical and Aerospace Engineering Due to an increasing demand for autonomous vehicles, considerable attention has been focused on vision-based control. Cameras are small, lightweight, and relatively inexpensive, making them an attractive alternative to other more traditional sensors, such as infrared and radar. Cameras provide a rich stream of data to describe the vehicle’s environment. These data can be analyzed to provide the controller with information such as the relative size and location of obstacles. Intelligent control decisions can then be made using this information in order to navigate the vehicle safely through the environment. This thesis focuses upon two fairly established visionbased control methodologies, optic flow and scene reconstruction. The advantages and disadvantages of each approach are analyzed. A multi-rate controller which merges these two approaches is introduced. It attempts to emphasize the advantages of each approach by alternating between the two, based on the characteristics of the environment. Two simulations validate the benefits of this multi-rate controller for the purposes of reactive obstacle avoidance and navigation. These simulations include a nonlinear F-16 model flying through a virtual scaled-up urban environment. Optic flow, scene reconstruction, and the multi-rate control approaches are applied to autonomously

Waypoint Navigation for a Micro Air Vehicle Using Vision-Based Attitude Estimation

Missions envisioned for micro air vehicles may require a high degree of autonomy to operate in unknown environments. As such, vision is a critical technology for mission capability. This paper discusses an autopilot that uses vision coupled with GPS and altitude sensors for waypoint navigation. The vision processing analyzes a horizon to estimate roll and pitch information. The GPS and altitude sensors then command values to roll and pitch for navigation between waypoints. A flight test of a MAV using this autopilot demonstrates the resulting closed-loop system is able to autonomously reach several waypoints. Several issues, such as estimating heading to account for slow updates, are investigated to increase performance.

A Mixed Local-Global Solution to Motion Planning within 3-D Environments

Autonomous flight through urban environments requires methods to generate trajectories that traverse a region and its associated obstacles. This paper introduces the development of a 3-dimensional motion planning algorithm using a random dense tree whose branches are motion primitives from a 3-dimensional version of the Dubins car called the Dubins airplane. The motion primitives consist of 3-dimensional maneuvers formulated as combinations of turn segments and straight segments with an associated constant rate of climb. The resulting motion planner builds the tree by pruning nodes that intersect 3-dimensional obstacles while connecting the remaining nodes with the motion primitives. An example demonstrates the motion planner can avoid building-style obstacles and even bridges using feasible paths that are sub-optimal solutions to minimize the cost of flight time.

Maneuvering and Tracking for a Micro Air Vehicle Using Vision-Based Feedback

Missions envisioned for micro air vehicles may require a high degree of autonomy to operate in unknown environments. As such, vision is a critical technology for mission capability. This paper discusses an autopilot that uses vision coupled with GPS and altitude sensors. One use of vision processing analyzes a horizon to estimate roll and pitch information. Another use tracks a feature point to estimate position relative to a target. This paper presents examples of waypoint navigation and homing using vision-based feedback. The examples indicate the vision provides sufficient information to achieve the missions.