GPU based generation of state transition models using simulations for unmanned surface vehicle trajectory planning

Abstract

This paper describes GPU based algorithms to compute state transition model for unmanned surface vehicles (USVs) using 6 degree of freedom (DOF) dynamics simulations of vehicle-wave interaction. State transition model is a key component of Markov Decision Process (MDP), which is a natural framework to formulate the problem of trajectory planning under motion uncertainty. USV trajectory planning problem is characterized by the presence of large and somewhat stochastic forces due to ocean waves, which can cause significant deviations in their motion. Feedback controllers are often employed to reject disturbances and get back on the desired trajectory. However, the motion uncertainty can be significant and must be considered in the trajectory planning to avoid collisions with the surrounding obstacles. In case of USV missions, state transition probabilities need to be generated on-board, to compute trajectory plans that can handle dynamically changing USV parameters and environment (e.g., changing boat inertia tensor due to fuel consumption, variations in damping due to changes in water density, variations in sea-state, etc.). The 6 DOF dynamics simulations reported in this paper are based on potential flow theory. We also present a model simplification algorithm based on temporal coherence and its GPU implementation to accelerate simulation computation performance. Using the techniques discussed in this paper we were able to compute state transition probabilities in less than 10 minutes. Computed transition probabilities are subsequently used in a stochastic dynamic programming based approach to solve the MDP to obtain trajectory plan. Using this approach, we are able to generate dynamically feasible trajectories for USVs that exhibit safe behaviors in high sea-states in the vicinity of static obstacles.

Model-predictive asset guarding by team of autonomous surface vehicles in environment with civilian boats

“…The outlined problem can be decomposed into multiple components, e.g., accelerated simulation Thakur et al 2012), trajectory planning for collisionfree guidance Švec et al (2011), Švec et al (2012), Thakur et al (2012), Švec et al (2013), Bertaska et al (2013), Švec et al (2013), learning of interception behaviors , and multi-agent task allocation and planning.…”

“…5.5 suggest that it is important for the predictive simulator to provide good estimates of utility. To address this issue in future work, we intend to perform experiments using a higher fidelity simulation environment Thakur et al 2012).…”

Path planning algorithm for unmanned surface vehicle formations in a practical maritime environment

“…It is the first work specifically solving the USV formation problem with algorithm practicability as the main feature of this research. A number of previous works have developed path planning algorithms for USVs; however, nearly all of them (Tam and Bucknall, 2013;Naeem et al, 2012;Thakur et al, 2012), with the notable exception of Kim et al (2014), simulated algorithms in simple self-constructed environments rather than real ocean environments. The algorithm designed in this paper is able to extract information from a real navigation map to construct a synthetic grid map, where both static and dynamic obstacles are well represented.…”

Application of a Chaotic Oscillator in an Autonomous Mobile Robot

“…That way and from their successful realizations, they are quite suitable for many engineering applications [4][5][6][7][8]. For instance, traditionally the control of robot systems has been implemented using computer program units (CPUs) [9], microcontrollers [10], etc. However, recently some researchers propose using chaotic oscillators to control autonomous mobile robots [11].…”