Online world modeling and path planning for an unmanned helicopter

Abstract

Mission scenarios beyond line of sight or with limited ground control station access require capabilities for autonomous safe navigation and necessitate a continuous extension of existing and potentially outdated information about obstacles. The presented approach is a novel synthesis of techniques for 3D environment perception and global path planning. A locally bounded sensor fusion approach is used to extract sparse obstacles for global incremental path planning in an anytime fashion. During the flight, a stereo camera checks the field of view along the flight path ahead by analyzing depth images. A 3D occupancy grid is built incrementally. To reduce the high data rate and storage demands of grid-type maps, an approximated polygonal world model is created. For a compacted representation, it uses prisms and ground planes. This enables the system to constantly renew and update its knowledge about obstacles. An incremental heuristic path planner uses both a-priori information as well as incremental obstacle updates to assure a collision-free path at any time. Mapping results from flight tests show the functionality of onboard world modeling from real sensor data. Path planning feasibility is demonstrated within a simulation environment considering world model changes inside the vehicle's field of view.

Certification and Software Verification Considerations for Autonomous Unmanned Aircraft

“…Whereas this work focuses on software verification and certification issues, a general overview about ARTIS can be found in [43], where the following onboard software components and functionalities for decisional autonomy are also summarized: 1) payload-directed mission elements (vision-based gate passing and vision-based ground vehicle tracking) [44], 2) real-time world modeling and path replanning [45,46], 3) online exploration behavior in urban terrain [47] (Fig. 2), 4) usage of a large urban terrain database (city of Berlin) [48], 5) composite flight behaviors that solve abstract guidance tasks (search pattern planning and safe perimeter tracking) [49], 6) trajectory following of linear segments and cubic splines [50], and 7) evaluation of the roadmap-based path planning (performance, smoothness, and safety) [51] (Fig.…”

Dependable Low‐altitude Obstacle Avoidance for Robotic Helicopters Operating in Rural Areas

“…Although many papers have been published on vision‐based obstacle avoidance for rotorcraft, very few systems have been implemented on an actual aircraft, and modest experimental results have been reported in the literature. In Andert and Adolf (), stereo vision has been used to build a world representation that combines occupancy grids and polygonal features. Experimental results on mapping are presented in the paper, but there are no results about path planning and obstacle avoidance.…”

An evaluation of stereo and laser‐based range sensing for rotorcraft unmanned aerial vehicle obstacle avoidance

“…Note that this sensor model does not reduce the occupancy probabilities in proportion to range squared, which would be a more accurate representation of stereo error characteristics (Andert & Adolf, 2009; Matthies & Shafer, 1987). An evaluation of the proposed stereo model and the one of (Andert & Adolf, 2009) was conducted and showed that incorporating the Gaussian error properties does not improve the results when large voxels are used (such as the 0.5‐m voxels we use). Because the resulting map is discretized at a coarse resolution, the extra fidelity offered by a Gaussian error model is lost.…”