This paper describes methodologies to estimate the collision probability, Euclidean distance and gradient between a robot and a surface, without explicitly constructing a free space representation. The robot is assumed to be an ellipsoid, which provides a tighter approximation for navigation in cluttered and narrow spaces compared to the commonly used spherical model. Instead of computing distances over point clouds or high-resolution occupancy grids, which is expensive, the environment is modeled using compact Gaussian mixture models and approximated via a set of ellipsoids. A parallelizable strategy to accelerate an existing ellipsoid-ellipsoid distance computation method is presented. Evaluation in 3D environments demonstrates improved performance over state-of-the-art methods. Execution times for the approach are within a few microseconds per ellipsoid pair using a single-thread on low-power embedded computers.

This paper introduces the open-source framework, GIRA, which implements fundamental robotics algorithms for reconstruction, pose estimation, and occupancy modeling using compact generative models. Compactness enables perception in the large by ensuring that the perceptual models can be communicated through low-bandwidth channels during large-scale mobile robot deployments. The generative property enables perception in the small by providing high-resolution reconstruction capability. These properties address perception needs for diverse robotic applications, including multi-robot exploration and dexterous manipulation. State-of-the-art perception systems construct perceptual models via multiple disparate pipelines that reuse the same underlying sensor data, which leads to increased computation, redundancy, and complexity. GIRA bridges this gap by providing a unified perceptual modeling framework using Gaussian mixture models (GMMs) as well as a novel systems contribution, which consists of GPUaccelerated functions to learn GMMs 10-100x faster compared to existing CPU implementations. Because few GMM-based frameworks are open-sourced, this work seeks to accelerate innovation and broaden adoption of these techniques.

This article presents a method for cave surveying in total darkness using an autonomous aerial vehicle equipped with a depth camera for mapping, downward-facing camera for state estimation, and forward and downward lights. Traditional methods of cave surveying are labor-intensive and dangerous due to the risk of injury when operating in darkness, and the potential structural instability of the subterranean environment. Although these dangers can be mitigated by deploying robots to map dangerous passages and voids, real-time feedback is often needed to operate robots safely and efficiently. Few state-of-the-art, high-resolution perceptual modeling techniques attempt to reduce their high bandwidth requirements to work well with low bandwidth communication channels. To bridge this gap in the state-of- the-art, this work compactly represents sensor observations as Gaussian mixture models and maintains a local occupancy grid map for a motion planner that greedily maximizes an information-theoretic objective function. The approach accommodates both limited field of view (FoV) depth cameras and larger FoV LiDAR sensors and is extensively evaluated in long duration simulations on an embedded PC. An aerial system is leveraged to demonstrate the repeatability of the approach in a flight arena as well as the effects of communication dropouts. Finally, the system is deployed in Laurel Caverns, a commercially owned and operated cave in southwestern Pennsylvania, USA, and a wild cave in West Virginia, USA. Videos of the simulation and hardware results are available athttps://youtu.be/iwi3p7IENjEandhttps://youtu.be/H8MdtJ5VhyU.

This paper presents a real-time, kinodynamic planning and information-theoretic exploration framework that enables high-resolution mapping of three-dimensional environments featuring complex concavities and disjoint objects. The proposed approach targets planetary exploration applications and seeks to achieve real-time operation on computationally constrained systems while ensuring energy-efficient information acquisition. Trajectories are selected by maximizing a measure of information gain per an expected execution cost (e.g., time or energy). The proposed trajectory generation formulation is based on state-lattice motion primitives and evaluation of the Cauchy-Schwarz quadratic mutual information (CSQMI) at each lattice state. An expanded search structure is proposed that extends the state-lattice to a finite horizon to enable expansive space coverage while remaining real-time viable. Additionally, compression techniques are employed to reduce the computational burden associated with the CSQMI calculation over expansive environments while preserving fidelity. The performance of the proposed methodology is evaluated through simulated exploration of a three-dimensional terrestrial pit environment by a quadrotor aerial robot which acts as a surrogate for a propulsive vehicle when operating on an airless body.