Collision Prediction and Optimal Trajectory Generation for Collision Avoidance Systems in Trackless Mobile Machines

Abstract

The continued high number of fatalities associated with Trackless Mobile Machines (TMMs) in South Africa have led to the introduction of Collision Avoidance System (CAS) regulations in the Mine Health and Safety Act in 2015. This has lead to the profusion of technologically-immature CASs from third-party vendors, all of which are centered on automatic stopping and braking systems. These braking systems often result in trivial or ineffective solutions, proving costly to mining operations. The combination of braking and steering control in CASs may substantially increase the solution space and provide far safer and more efficient manoeuvres. A recursive non-linear collision prediction estimator and optimal trajectory generation model was developed to evaluate the potential contribution of the addition of steering to CASs. Three independent optimal trajectory generation models are proposed to compete against one another in an attempt to synthesize the safest, most predictable, and efficient trajectory. A deep reinforcement learning, lattice optimization and Monte Carlo hyper sampling path planning model’s trajectories are evlauated using the Earth Moving Equipment Safety Round Table (EMESRT) interaction scenarios. Initial results indicate increased CAS solution spaces in collision-avoiding scenarios, providing safer and more effective solutions in high velocity vehicle interactions.