Local path planning using a new artificial potential function composition and its analytical design guidelines

This paper presents a new framework for path planning based on artificial potential functions (APFs). In this scheme, the APFs for path planning have a multiplicative and additive composition between APFs for goal destination and APFs for obstacle avoidance, unlike conventional composition where the APF for obstacle avoidance is added to the APF for goal destination. In particular, this paper presents a set of analytical guidelines for designing potential functions to avoid local minima for a number of representative scenarios based on the proposed framework for path planning. Specifically the following cases are addressed: (i) a non-reachable goal problem (a case in which the potential of the goal is overwhelmed by the potential of an obstacle), (ii) an obstacle collision problem (a case in which the potential of the obstacle is overwhelmed by the potential of the goal) and (iii) a narrow passage problem (a case in which the potential of the goal is overwhelmed by the potential of two obstacles). The example results for each case show that the proposed scheme can effectively construct a path-planning system with the capability of reaching a goal and avoiding obstacles despite possible local minima.     

Tool support for learning Büchi automata and linear temporal logic

We introduce a graphical interactive tool, named GOAL, that can assist the user in understanding Büchi automata, linear temporal logic, and their relation. Büchi automata and linear temporal logic are closely related and have long served as fundamental building blocks of linear-time model checking. Understanding their relation is instrumental in discovering algorithmic solutions to model checking problems or simply in using those solutions, e.g., specifying a temporal property directly by an automaton rather than a temporal formula so that the property can be verified by an algorithm that operates on automata. One main function of the GOAL tool is translation of a temporal formula into an equivalent Büchi automaton that can be further manipulated visually. The user may edit the resulting automaton, attempting to optimize it, or simply run the automaton on some inputs to get a basic understanding of how it operates. GOAL includes a large number of translation algorithms, most of which support past temporal operators. With the option of viewing the intermediate steps of a translation, the user can quickly grasp how a translation algorithm works. The tool also provides various standard operations and tests on Büchi automata, in particular the equivalence test which is essential for checking if a hand-drawn automaton is correct in the sense that it is equivalent to some intended temporal formula or reference automaton. Several use cases are elaborated to show how these GOAL functions may be combined to facilitate the learning and teaching of Büchi automata and linear temporal logic. This work was partially supported by the National Science Council, Taiwan (R.O.C.) under grants NSC94-2213-E-002-089, NSC95-2221-E-002-127, NSC95-3114-P-001-001-Y02 (iCAST 2006), NSC96-3114-P-001-002-Y (iCAST 2007), and NSC97-2221-E-002-074-MY3.     

融合认知行为模型的深度强化学习框架及算法

面对高维连续状态空间或稀疏奖励等复杂任务时,仅依靠深度强化学习算法从零学习最优策略十分困难,如何将已有知识表示为人与学习型智能体之间相互可理解的形式,并有效地加速策略收敛仍是一个难题.对此,提出一种融合认知行为模型的深度强化学习框架,将领域内先验知识建模为基于信念-愿望-意图(belief- desire-intention, BDI)的认知行为模型,用于引导智能体策略学习.基于此框架,分别提出融合认知行为模型的深度Q学习算法和近端策略优化算法,并定量化设计认知行为模型对智能体策略更新的引导方式.最后,通过典型gym环境和空战机动决策对抗环境,验证所提出算法可以高效利用认知行为模型加速策略学习,有效缓解状态空间巨大和环境奖励稀疏的影响.     

HEURISTIC MODELING FOR A DYNAMIC AND GOAL PROGRAMMING IN PRODUCTION PLANNING OF CONTINUOUS MANUFACTURING SYSTEMS

At the first sight it seems that advanced operation research is not used enough in continuous production systems as comparison with mass production, batch production and job shop systems, but really in a comprehensive evaluation the advanced operation research techniques can be used in continuous production systems in developing countries very widely, because of initial inadequate plant layout, stage by stage development of production lines, the purchase of second hand machineries from various countries, plurality of customers. A case of production system planning is proposed for a chemical company in which the above mentioned conditions are almost presented. The goals and constraints in this issue are as follows: ① Minimizing deviation of customer's requirements. ② Maximizing the profit. ③ Minimizing the frequencies of changes in formula production. ④ Minimizing the inventory of final products. ⑤ Balancing the production sections with regard to rate in production. ⑥ Limitation in inventory of raw material. The present situation is in such a way that various techniques such as goal programming, linear programming and dynamic programming can be used. But dynamic production programming issues are divided into two categories, at first one with limitation in production capacity and another with unlimited production capacity. For the first category, a systematic and acceptable solution has not been presented yet. Therefore an innovative method is used to convert the dynamic situation to a zero- one model. At last this issue is changed to a goal programming model with non-linear limitations with the use of GRG algorithm and that's how it is solved.