Extending the Path-Planning Horizon

Abstract

SINCE typical mobile robotic vehicles have mobility sensors (such as LADAR or stereo) that can only acquire data up to a few tens of meters, a navigation system has no knowledge about the world beyond this sensing horizon. As a result, path planners that rely only on this knowledge to compute paths are unable to anticipate obstacles sufficiently early and has no choice than to plan inefficient paths that trace obstacle boundaries. To alleviate this problem, We present an opportunistic navigation and view planning strategy that incorporates look-ahead sensing of possible obstacle configurations. This planning strategy is based on a "what-if" analysis of hypothetical future configurations of the environment. Candidate vantage positions are evaluated based on their ability of observing anticipated obstacles. These vantage positions identified by this forward-simulation framework are used by the planner as intermediate waypoints.The validity of the strategy is supported by results from simulations as well as field experiments with a real robotic platform. These results also show that opportunistically significant reduction in path length can be achieved by using this framework. The reconstructed epipolar geometry from the very wide baseline100 A.9The ratio of the height over the width of the window on the left is 1.5456 and the window on the right 1.8356, which gives us an indication of the reconstruction quality. This effect is due to the fact that the planner is limited by the maximum range of the mobility sensors. Since typical mobility sensors, such as Laser Radar (LADAR) or passive stereo vision, will only acquire data up to a few tens of meters, the planner has no knowledge about what to encounter beyond the sensed perimeter. As a result, the planner is unable to anticipate obstacles sufficiently early and has no choice but to plan paths close to obstacle boundaries.For autonomous navigation over long distances, this issue degrades the performance of the system by greatly increasing the length of the path traveled by the vehicle. Consequently, the power consumed is increased and, more importantly, CHAPTER 1. INTRODUCTION FIGURE 1.1. Typical example of poor performance due to lack of sensor planning and mid-range sensing (Left: Overhead view of terrain; Right: Executed path with detected obstacles shown as shaded regions). The path from S1 to G1 intersects a large hill which is discovered only when the vehicle enters a large cul-de-sac, causing the executed path to be substantially more expensive than the path that would have been followed, had the obstruction been discovered earlier. (From [114]) the risk of exposure to threats is also increased. In addition, the relative short range of the mobility sensors forces the vehicle to drive closer to terrain obstructions than is safe or necessary.One solution is to use sensors with longer range to acquire information about the terrain further ahead. However, to use these sensors one needs to take into account certain constraints about the sensing geom...

Path planning with variable-fidelity terrain assessment

“…Nabbe and Herbert [12] have work that deals with planning beyond the sensor horizon or through areas where insufficient data has been collected. When determining a path, the cost of acquiring data is considered during path planning.…”

Motion Planning Using Predicted Perceptive Capability

“…Other work seeks to combine navigation and view planning by hallucinating potential look-ahead sensor observations to extend the path planning horizon and achieve a reduction in path length. 11 Also related is work 4 that computes a 'confidence-of-perception' measure to decide where to next perform sensing, effectively tackling the view planning problem. Further related work explicitly considers visual servo performance during the planning process by augmenting the robot configuration with image-features to arrive at the so-called perceptual control manifold.…”

Humanoid navigation planning using future perceptive capability

“…However, scenarios considered are often amenable to purely geometric reasoning about visibility, and make application to high-DOF systems challenging. Other work seeks to combine navigation and view planning by hallucinating potential look-ahead sensor observations to extend the path planning horizon and achieve a reduction in path length [7]. Also related is work [8] that computes a 'confidence-of-perception' measure to decide where to next perform sensing, effectively tackling the view planning problem.…”