Maze Search Using Reinforcement Learning by a Mobile Robot
Journal Title: Advances in Robotics & Mechanical Engineering - Year 2018, Vol 1, Issue 2
Abstract
This review presents on research of application of reinforcement learning and new approaches on a course search in mazes with some kinds of multi-point passing as machines. It is based on a selective learning from multi-directive behavior patterns using PS (Profit Sharing) by an agent. The behavior is selected stochastically from 4 kinds of ones using PS with Boltzmann Distribution with a plan to inhibit invalid rules by a reinforcement function of a geometric sequence. Moreover, a variable temperature scheme is adopted in this distribution, where the environmental identification is valued in the first stage of the search and the convergence of learning is shifted to be valuing as time passing. A SUB learning system and a multistage layer system were proposed in this review, and these functions were inspected by some simulations and experiments using a mobile robot.In robots which has begun to spread to not only industrial world but also general home, e.g. cleaning robots etc., recently achievement of complex tasks and adaptation of complex environment has been required and can be done by agents which were concept of distributed artificial intelligent and caught abstractly various robots. Conventionally, as behavior of agents has been controlled by rules designed as if then rules, a lot of rules were required for adaptation to complex environment and achievement of complex tasks.
Authors and Affiliations
Makoto Katoh, Keiichi Tanaka, Shunsuke Shikichi
Keywords
Related Articles
- EP ID EP580565
- DOI 10.32474/ARME.2018.01.000110
- Views 100
- Downloads 0
Some Issues Concerned with PMU-Based Security Control of Electric Interconnected Systems
The increasing consumption of electrical energy requires higher capacity both in generation as in transmission of electric power and expansion of the networks, including interconnection of systems and High Voltage Direct...
Research on Fishery Water Quality Detection System of Unmanned Aerial Vehicle
Many lands in China are close to rivers and oceans and they are very suitable for developing fisheries. Water quality monitoring is indispensable to the development of fisheries. Therefore, a method of detecting, evaluat...
Modeling the Temperature of the Evacuation Chamber with Artificial Neural Networks
This investigation approaches the artificial neural networks applied to the ore drying process in carbonate-ammonia leaching. To carry out this research, the main variables that characterize the process were identified....
Insight Looks to Soft (Continuum) Robotics
Soft Robotics is emerging fresh sub field in Robotics which is very useful in medical, industry, space exploration, deep sea exploration, Nano-robotics and many more likewise applications. The major benefit of Soft Robot...
Insight Bigdata Management Modeling for Business Virtualization
Bigdata design, development and implementation are emerging need of today’s Business Virtualization and future world strongly depend on this emerging and needful technology of Bigdata and Bigdata management to generate B...