Redirigiendo al acceso original de articulo en 18 segundos...
Inicio  /  Applied Sciences  /  Vol: 9 Par: 7 (2019)  /  Artículo
ARTÍCULO
TITULO

Integrating a Path Planner and an Adaptive Motion Controller for Navigation in Dynamic Environments

Junjie Zeng    
Long Qin    
Yue Hu    
Quanjun Yin and Cong Hu    

Resumen

Since an individual approach can hardly navigate robots through complex environments, we present a novel two-level hierarchical framework called JPS-IA3C (Jump Point Search improved Asynchronous Advantage Actor-Critic) in this paper for robot navigation in dynamic environments through continuous controlling signals. Its global planner JPS+ (P) is a variant of JPS (Jump Point Search), which efficiently computes an abstract path of neighboring jump points. These nodes, which are seen as subgoals, completely rid Deep Reinforcement Learning (DRL)-based controllers of notorious local minima. To satisfy the kinetic constraints and be adaptive to changing environments, we propose an improved A3C (IA3C) algorithm to learn the control policies of the robots? local motion. Moreover, the combination of modified curriculum learning and reward shaping helps IA3C build a novel reward function framework to avoid learning inefficiency because of sparse reward. We additionally strengthen the robots? temporal reasoning of the environments by a memory-based network. These improvements make the IA3C controller converge faster and become more adaptive to incomplete, noisy information caused by partial observability. Simulated experiments show that compared with existing methods, this JPS-IA3C hierarchy successfully outputs continuous commands to accomplish large-range navigation tasks at shorter paths and less time through reasonable subgoal selection and rational motions.

 Artículos similares

       
 
Nezar Sahbon and Michal Welcer    
The accuracy of aerodynamically controlled guided projectile simulations is largely determined by the aerodynamic model employed in flight simulations which impacts vehicle interaction with the surrounding air. In this work, the performance of projectile... ver más
Revista: Aerospace

 
Xu Han, Xianku Zhang and Hugan Zhang    
Trajectory planning aims to provide a time-related control target that contains the concerned states. For an underactuated surface vehicle (USV), planning challenges include limitations on curvature, speed, acceleration, and jerk. These challenges are re... ver más

 
Lennart Lobitz, Hendrik Traub, Mats Overbeck, Maximilian Bien, Sebastian Heimbs, Christian Hühne, Jens Friedrichs and Peter Horst    
Laminar flow offers significant potential for increasing the energy-efficiency of future transport aircraft. The German Cluster of Excellence SE2A is developing a new approach for hybrid laminar flow control. The concept aims to maintain laminar flow up ... ver más
Revista: Aerospace

 
Ye Qiu, Haijun Wei, Daping Zhou and Jingming Li    
In this study, the effect of mixing a small amount of ammonia on the ignition delay time of methyl decanoate under different conditions was studied from the perspective of the combustion mechanism. The effect of adding ammonia on the ignition delay time ... ver más

 
Vincenzo Bonaiuto and Andrea Zanela    
This paper focuses on integrating a laser rangefinder system with an anthropomorphic robot (NAO6?Aldebaran, United Robotics Group) to improve its sensory and operational capabilities, as part of a larger project concerning the use of these systems in ?as... ver más