Perception for a river mapping robot

Abstract

Abstract-Rivers with heavy vegetation are hard to map from the air. Here we consider the task of mapping their course and the vegetation along the shores with the specific intent of determining river width and canopy height. A complication in such riverine environments is that only intermittent GPS may be available depending on the thickness of the surrounding canopy. We present a multimodal perception system to be used for the active exploration and mapping of a river from a small rotorcraft flying a few meters above the water. We describe three key components that use computer vision, laser scanning, and inertial sensing to follow the river without the use of a prior map, estimate motion of the rotorcraft, ensure collisionfree operation, and create a three dimensional representation of the riverine environment. While the ability to fly simplifies the navigation problem, it also introduces an additional set of constraints in terms of size, weight and power. Hence, our solutions are cognizant of the need to perform multi-kilometer missions with a small payload. We present experimental results along a 2km loop of river using a surrogate system.

Autonomous Exploration and Motion Planning for an Unmanned Aerial Vehicle Navigating Rivers

“…The initial version of the approach to generate the river maps was presented in Chambers et al. (), and current details are presented in Section .…”

“…This paper builds on our existing work in river environments for autonomous perception, positioning, and obstacle avoidance work (Achar, Sankaran, Nuske, Scherer, & Singh, ; Chambers et al., ; Cover, Choudhury, Scherer, & Singh, ; Rehder, Gupta, Nuske, & Singh, ; Scherer et al., ) and extends to contribute the key capabilities of the following: 1.A modified low‐level motion planning algorithm called SPARTAN‐lite (where SPARTAN denotes Sparse Tangential Network) that exploits geodesic properties on smooth tangential manifolds around obstacles. …”

“…There is a need for a lightweight planner that computes only when it needs to and sits idle otherwise. We present a motion planner that leverages the intermittent sparsity of its environment and creates plans several times faster than the state‐of‐the‐art (Chambers et al., ). The planner constructs a graph wrapped in a tangential surface around obstacles.…”

River mapping from a flying robot: state estimation, river detection, and obstacle mapping

“…The fourth contribution is a short range, laser-ranging based system tasked with obstacle detection and the creation of a metric, three-dimensional map. Parts of our system were first shown in Chambers et al (2011) and Achar et al (2011). Since then our approaches have been refined to reflect our latest results.…”