Service robot planning via solving constraint satisfaction problem

Abstract

The problem of demographic shifts towards the elderly is deteriorating, as the relative number of caregivers is insufficient to provide the support required for their wellbeing, which is further aggravated by the increasingly hectic lifestyle. Service robot is getting more prominent as a possible solution. Robot manipulation and mobility is an important field, but they also require high level planning for these minute actions in order to provide ample support. Automatic service composition, contributed significantly by web services, offers the necessary technology for the task. Robot planning problem can be solved by representing it as constraint satisfaction problem (CSP) due to it being able to support loose binding of services and variables of wider domain. This paper further extends the structure of the CSP planner to enable intelligent decision-making. Besides, standardization is made on the properties and relationships of objects such that planning rules can be easily generated from knowledge base. Services and their corresponding terms are designed for efficient planning. Case studies show that the system is able to perform tasks bounded by complex logical rules. It also provides valuable insights into future enhancements and research.

Development and Evaluation of the Traction Characteristics of a Crawler EOD Robot

“…Currently, mobile robotics is at the intersection of several fields of science. These systems include: Knowledge representation [21]: the field of artificial intelligence helps to obtain an internal model of the world associated with the task performed by the robot, and uses data structures and specific algorithms to represent the characteristics of objects in the environment; Natural language [22]: natural language changes quite frequently, so simple word recognition is no longer enough to understand the real meaning of a processed text; Learning [23]: ideally, a robot could learn the tasks it has to perform by simply repeating similar actions performed by a human operator; Planning and problem solving [24]: intelligence is inherently associated with the ability to plan actions needed to achieve a particular goal, as well as the ability to solve problems that arise when these action plans do not work; Inference [25]: by inference, it is possible to fill in the missing information to solve a certain problem; Search [26]: in terms of artificial intelligence, search means the efficient examination of a representation of knowledge, specific to a certain problem (search in a "space") in order to determine a solution; Vision [27]: by creating artificial vision systems, the actions of the mobile robot can be made more precise and complex. Sometimes, mobile robots appear in the form of vehicles capable of operating autonomously on the ground (UGVs-Unmanned Ground Vehicles), in the air (UAVs-Unmanned Aerial Vehicles) or in the water (UUVs-Unmanned Undersea Vehicles).…”

“…Learning [23]: ideally, a robot could learn the tasks it has to perform by simply repeating similar actions performed by a human operator; Planning and problem solving [24]: intelligence is inherently associated with the ability to plan actions needed to achieve a particular goal, as well as the ability to solve problems that arise when these action plans do not work; Inference [25]: by inference, it is possible to fill in the missing information to solve a certain problem; Search [26]: in terms of artificial intelligence, search means the efficient examination of a representation of knowledge, specific to a certain problem (search in a "space") in order to determine a solution; Vision [27]: by creating artificial vision systems, the actions of the mobile robot can be made more precise and complex. Sometimes, mobile robots appear in the form of vehicles capable of operating autonomously on the ground (UGVs-Unmanned Ground Vehicles), in the air (UAVs-Unmanned Aerial Vehicles) or in the water (UUVs-Unmanned Undersea Vehicles).…”

Weighted Constraint Satisfaction for Smart Home Automation and Optimization

“…The former can be achieved through service composition via association with SWRL or SPARQL language [8]. The latter can have a built-in path finding algorithm that works with high level planning, where high level planning has to ensure proper working environment for low-level functions [9]. Theoretically, planning itself can handle all the tasks, including device association and low-level path finding.…”

BSplines Properties with Interval Analysis for Constraint Satisfaction Problem: Application in Robotics

“…Solving Constraint Satisfaction Problem (CSP) comes down to compute the feasible space of a set of variables that ensures a set of constraints. CSP has many applications in robotics: they are used in planning [1], sequential manipulation planning [2], robot control [3] and are applied to several tasks such as grasping, painting, stripping, etc. In robotics, those constraints may be the robot kinematic and dynamic limits, or the ones imposed by the desired task.…”