TASK PLANNING AND ACTION COORDINATION IN INTEGRATED SENSOR-BASED ROBOTS

Intelligent robots interact with the real world by employing their adv anced sensory mechanisms to perceive their environment, and using thei r effecters and tools to change the state of their environment, Some o f the important capabilities which endow ''intelligence'' to those rob ots include, (1) planning, i.e., given a goal, the ability to generate a set of task plans which will lead to achieving the goal, (2) coordi nation and execution of the perceptual actions, i.e., the abilities to coordinate sensors, acquire sensory data, and process, interpret and transform the sensory information, and (3) coordination and execution of the motor actions, i.e., the ability to navigate in their environme nts and the ability to coordinate effecters and tools and manipulate o bjects to accomplish assigned tasks, In this paper we introduce a Syst em Architecture for Sensor-based Intelligent Robots (SASIR). The syste m architecture consists of Perception, Motor, Task Planner, Knowledge- Base, User Interface and Supervisor modules, SASIR is constructed usin g a frame data structure, which provides a suitable and flexible schem e for representation and manipulation of the world model, the sensor d erived information, as well as for describing the actions required for the execution of a specific task, The experimental results show the b asic validity of the general architecture as well as the robust and su ccessful performance of two working systems: (1) the Autonomous Spill Cleaning (ASC) Robotic System, and (2), ROBOSIGHT, which is capable of a range of autonomous inspection and manipulation tasks, Simulation a nd animation techniques were employed, in addition to the real-world t esting, during the system development, The system components were succ essfully transported to another research laboratory involving a differ ent type of robot, different sensors, and a different physical environ ment.