An efficient system for combined route traversal and collision avoidance

Abstract

Here we consider the problem of a robot that must follow a previously designated path outdoors. While the nominal path, a series of closely spaced via points, is provided with an assurance that it will lead to the destination, we can't be guaranteed that it will be obstacle free. We present an efficient system capable of both following the path as well as being perceptive and agile enough to avoid obstacles in its way. We present a system that detects obstacles using laser ranging, as well as a layered system that continuously tracks the path, avoiding obstacles and replanning the route when necessary. The distinction of this system is that compared to the state of the art, it is minimal in sensing and computation while achieving high speeds. In this paper, we present an algorithm that is based on models of obstacle avoidance by humans and show variations of the model to deal with practical considerations. We show how the parameters of this model are automatically learned from observation of human operation and discuss limitations of the model. We then show how these models can be extended by adding online route planning and a formulation that allows for operation at varying speeds. We present experimental results from an autonomous vehicle that has operated several hundred kilometers to validate the methodology.

Expanded Guide Circle-based Obstacle Avoidance for the Remotely Operated Mobile Robot

“…Therefore, Step 2 -4 is not necessary, and the mobile robot is controlled using the original operation command in (4). If r IGC is less than r max , the mobile robot will be guided through the fusion of the operator's command and the guiding command produced by the expanded GC.…”

“…[1][2][3][4]. In many applications, the mobile robot should be partially or fully operated by the human operator because of the technical limitations of the autonomous mobility.…”

A practical obstacle detection system for autonomous orchard vehicles

“…Perhaps the most common solution for obstacle detection consists in installing the lasers on an active sweeping mechanism, e.g., as in [3], [6], [17]. By commanding the mechanism actuator, it is possible to change the orientation of the laser to measure the terrain from multiple perspectives, reducing effects of occlusion, mixed pixels and sunlight.…”

High level assisted control mode based on SLAM for a remotely controlled robot

“…The reactive component projects a number of arcs in front of the robot and chooses the one that best combines the following criteria: follow the path given by the deliberative component, avoid the obstacle that are nearby and go towards a free space. The same layered approach (plan globally and react locally) to navigation in unknown environments is found in [11], used with a rovertype robot. The global planner uses A* to compute a new path, when needed.…”