Multi-ordered short-range mover prediction models for tracking and avoidance

This paper introduces a framework and methods that can be used to predict the movements of intelligent moving bodies in the presence of perceived static and dynamic environmental stimulus, such as terrain and weather influences. These methods are especially important for Intelligent-Autonomous Mobile (I-AM) Systems, where they can improve upon contemporary methods for tracking and avoidance by allowing I-AM systems to act or react based on enhanced predictions. These methods can also complement Cooperative Behavior Control (CBC) strategies of distributed, multi-agent systems wherein cooperation can be in the form of prediction rather than direct communication. Probability spatial distributions for intelligent moving objects, with respect to First-Order, Second-Order, and Third-Order predictions, have been formulated. This is a novel method since most prediction approaches use Kalman Filters to estimate future states based solely on previously observed states. Most prediction models do not take into consideration mobility characteristics (e.g., Ackermann Steering), nor the probable decision making capabilities of intelligent entities. By adding higher levels of fidelity to prediction models, more accurate and precise object tracking, and obstacle avoidance and/or engagement can be accomplished with already proven techniques.