Cognitive behavior modeling of agent is an important component of simulation system,and there are some difficulties in the simulation of course teaching.When students make simulation experiments about cognitive behavi...Cognitive behavior modeling of agent is an important component of simulation system,and there are some difficulties in the simulation of course teaching.When students make simulation experiments about cognitive behavior modeling,such as algorithm design and model construction,there is no simulation competition platform that is controllable,flexible and scalable.To solve this problem,we propose a simulation competition platform based on cognitive behavior modeling,called TankSim,for undergraduate and graduate students.This platform aims to cultivate studenfs team collaboration and innovation capability,and improve their learning motivation.This paper elaborates the proposed platform from three aspects,including demand analysis,platform design,and content design.展开更多
Due to long-term lack of comprehensive practice platform in simulation courses,students suffer from the challenges of engineering ability and systemic thinking training restrictions,"teaching"and“learning”...Due to long-term lack of comprehensive practice platform in simulation courses,students suffer from the challenges of engineering ability and systemic thinking training restrictions,"teaching"and“learning”separation,etc.To solve those problems,our teaching group created a simulation competition platform independently for theoretical and practical teaching of"Game Simulation&Modelmg" course.The introduction of competition platform has played a good role in stimulating students' learning motivation,training systemic simulation knowledge points and engineering ability,promoting theoretical and practical teaching,and enriching teaching materials through students'feedback and practice accumulation.展开更多
In the context of robotics, configuration space (c- space) is widely used for non-circular robots to engage tasks such as path planning, collision check, and motion planning. In many real-time applications, it is im...In the context of robotics, configuration space (c- space) is widely used for non-circular robots to engage tasks such as path planning, collision check, and motion planning. In many real-time applications, it is important for a robot to give a quick response to the user's command. Therefore, a constant bound on planning time per action is severely im- posed. However, existing search algorithms used in c-space gain first move lags which vary with the size of the under- lying problem. Furthermore, applying real-time search algo- rithms on c-space maps often causes the robots being trapped within local minima. In order to solve the above mentioned problems, we extend the learning real-time search (LRTS) algorithm to search on a set of c-space generalized Voronoi diagrams (c-space GVDs), helping the robots to incremen- tally plan a path, to efficiently avoid local minima, and to ex- ecute fast movement. In our work, an incremental algorithm is firstly proposed to build and represent the c-space maps in Boolean vectors. Then, the method of detecting grid-based GVDs from the c-space maps is further discussed. Based on the c-space GVDs, details of the LRTS and its implemen- tation considerations are studied. The resulting experiments and analysis show that, using LRTS to search on the c-space GVDs can 1) gain smaller and constant first move lags which is independent of the problem size; 2) gain maximal clear- ance from obstacles so that collision checks are much re- duced; 3) avoid local minima and thus prevent the robot from visually unrealistic scratching.展开更多
基金Natural Science Foundation of Hunan Province(Project number:2017JJ3371).
文摘Cognitive behavior modeling of agent is an important component of simulation system,and there are some difficulties in the simulation of course teaching.When students make simulation experiments about cognitive behavior modeling,such as algorithm design and model construction,there is no simulation competition platform that is controllable,flexible and scalable.To solve this problem,we propose a simulation competition platform based on cognitive behavior modeling,called TankSim,for undergraduate and graduate students.This platform aims to cultivate studenfs team collaboration and innovation capability,and improve their learning motivation.This paper elaborates the proposed platform from three aspects,including demand analysis,platform design,and content design.
基金Natural Science Foundation of Hunan Province(Project number:2017JJ3371).
文摘Due to long-term lack of comprehensive practice platform in simulation courses,students suffer from the challenges of engineering ability and systemic thinking training restrictions,"teaching"and“learning”separation,etc.To solve those problems,our teaching group created a simulation competition platform independently for theoretical and practical teaching of"Game Simulation&Modelmg" course.The introduction of competition platform has played a good role in stimulating students' learning motivation,training systemic simulation knowledge points and engineering ability,promoting theoretical and practical teaching,and enriching teaching materials through students'feedback and practice accumulation.
文摘In the context of robotics, configuration space (c- space) is widely used for non-circular robots to engage tasks such as path planning, collision check, and motion planning. In many real-time applications, it is important for a robot to give a quick response to the user's command. Therefore, a constant bound on planning time per action is severely im- posed. However, existing search algorithms used in c-space gain first move lags which vary with the size of the under- lying problem. Furthermore, applying real-time search algo- rithms on c-space maps often causes the robots being trapped within local minima. In order to solve the above mentioned problems, we extend the learning real-time search (LRTS) algorithm to search on a set of c-space generalized Voronoi diagrams (c-space GVDs), helping the robots to incremen- tally plan a path, to efficiently avoid local minima, and to ex- ecute fast movement. In our work, an incremental algorithm is firstly proposed to build and represent the c-space maps in Boolean vectors. Then, the method of detecting grid-based GVDs from the c-space maps is further discussed. Based on the c-space GVDs, details of the LRTS and its implemen- tation considerations are studied. The resulting experiments and analysis show that, using LRTS to search on the c-space GVDs can 1) gain smaller and constant first move lags which is independent of the problem size; 2) gain maximal clear- ance from obstacles so that collision checks are much re- duced; 3) avoid local minima and thus prevent the robot from visually unrealistic scratching.