Action-Based Models for Belief-Space Planning
نویسندگان
چکیده
Autonomy requires robots to learn models of the environment or objects while simultaneously searching for solutions in the partially observable state space. A flexible representation that supports incremental acquisition of models has several advantages for solving such tasks. In this paper, we investigate the use of graphs to capture the interaction statistics of an agent with aspects of the environment. We present a planner that employs a set of incomplete models for action selection. The approach is evaluated using the Robonaut 2 simulation in the context of object modeling and planning.
منابع مشابه
Balancing Detail and Abstraction in Belief-Space Planning for Robotics
Belief-space planning (BSP) has limited usage in robotics as methods quickly become computationally intractable with a growing number of states, observations, and actions. On the other hand, the tasks that can be defined and the solutions that can be found depend on the granularity of states, actions, and observations. As a result, the capabilities and performance of planning and reasoning syst...
متن کاملIntegrated robot task and motion planning in belief space
In this paper, we describe an integrated strategy for planning, perception, state-estimation and action in complex mobile manipulation domains. The strategy is based on planning in the belief space of probability distribution over states. Our planning approach is based on hierarchical goal regression (pre-image back-chaining). We develop a vocabulary of fluents that describe sets of belief stat...
متن کاملAugmenting BDI Agents with Deliberative Planning Techniques
Belief-Desire-Intention (BDI) agents are well suited for autonomous applications in dynamic environments. Their precompiled plan schemata contain the procedural knowledge of an agent and contribute to the performance. The agents generally are constrained to a fixed set of action patterns. Their choice depends on current goals, not on the future of the environment. Planning techniques can provid...
متن کاملAnalysis and Assessment of Communicative Action Indicators and Variables; a Case of Tehran city, Iran
While there are a wide variety of studies about communicative action theory of Habermas, there is the need for building of indicators and variables for quantitative methods of assessing this concept in a particular case study. Especially as the development of communicative action theory has created new perspectives in urban planning, it is necessary to assess and promote this concept in cities ...
متن کاملIntegrated task and motion planning in belief space
We describe an integrated strategy for planning, perception, state-estimation and action in complex mobile manipulation domains based on planning in the belief space of probability distributions over states using hierarchical goal regression (pre-image back-chaining). We develop a vocabulary of logical expressions that describe sets of belief states, which are goals and subgoals in the planning...
متن کامل