GPU-Accelerated Multi-Objective Optimal Planning in Stochastic Dynamic Environments
نویسندگان
چکیده
The importance of autonomous marine vehicles is increasing in a wide range ocean science and engineering applications. Multi-objective optimization, where trade-offs between multiple conflicting objectives are achieved (such as minimizing expected mission time, energy consumption, environmental harvesting), crucial for planning optimal routes stochastic dynamic environments. We develop multi-objective path planner flows by further developing improving our recently developed end-to-end GPU-accelerated single-objective Markov Decision Process planner. MDPs with scalarized rewards formulated solved idealized environments obstacles. Three simulated scenarios completed to elucidate approach capabilities: (i) an agent moving from start target travel time net-energy consumption when harvesting solar uncertain flow; (ii) and-energy uncertainties obstacle initial positions; (iii) attempting cross shipping channel while avoiding fast ships flow. Optimal operating curves computed fraction the that would be required existing solvers algorithms. Crucially, solution can serve benchmark other approximate AI algorithms such Reinforcement Learning help improve explainability those models.
منابع مشابه
Multi-Objective 4D Vehicle Motion Planning in Large Dynamic Environments
This paper presents Multi-Step A* (MSA*), a search algorithm based on A* for multi-objective 4D vehicle motion planning (three spatial and one time dimension). The research is principally motivated by the need for offline and online motion planning for autonomous Unmanned Aerial Vehicles (UAVs). For UAVs operating in large, dynamic and uncertain 4D environments, the motion plan consists of a se...
متن کاملGPU Accelerated Stochastic Simulation
Through computational methods, biologists are able learn more about molecular biology by building accurate models. These models represent and predict the reactions among species populations within a system. One popular method to develop predictive models is to use a stochastic, Monte Carlo method developed by Gillespie called the stochastic simulation algorithm (SSA). Since this algorithm is ba...
متن کاملOptimal Multi-Objective Planning of Distribution System with Distributed Generation
This paper presents a multi-objective formulation for optimal siting and sizing of distributed generation (DG) resources in distribution systems in order to minimize the cost of power losses and energy not supplied. The implemented technique is based on a genetic algorithm (GA) and weight method that employed to obtain the best compromise between these costs. Simulation results on 33-bus distri...
متن کاملTime optimal trajectory planning in dynamic environments
This paper presents a method for motion planning in dynamic environments, subject to robot dynamics and ac-tuator constraints. The time optimal trajectory is computed by rst generating an initial guess using the concept of velocity obstacle. The initial guess, computed by a global search over a tree of avoidance maneuvers, is then optimized using a dynamic optimization. This method is applicabl...
متن کاملoptimal multi-objective planning of distribution system with distributed generation
this paper presents a multi-objective formulation for optimal siting and sizing of distributed generation (dg) resources in distribution systems in order to minimize the cost of power losses and energy not supplied. the implemented technique is based on a genetic algorithm (ga) and weight method that employed to obtain the best compromise between these costs. simulation results on 33-bus distri...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Journal of Marine Science and Engineering
سال: 2022
ISSN: ['2077-1312']
DOI: https://doi.org/10.3390/jmse10040533