Robots need task planning algorithms to sequence actions toward accomplishing goals that are impossible through individual actions. Off-the-shelf task planners can be used by intelligent robotics practitioners to solv...Robots need task planning algorithms to sequence actions toward accomplishing goals that are impossible through individual actions. Off-the-shelf task planners can be used by intelligent robotics practitioners to solve a variety of planning problems. However, many different planners exist, each with different strengths and weaknesses,and there are no general rules for which planner would be best to apply to a given problem. In this study, we empirically compare the performance of state-of-the-art planners that use either the planning domain description language(PDDL) or answer set programming(ASP) as the underlying action language. PDDL is designed for task planning, and PDDL-based planners are widely used for a variety of planning problems. ASP is designed for knowledge-intensive reasoning, but can also be used to solve task planning problems. Given domain encodings that are as similar as possible, we find that PDDL-based planners perform better on problems with longer solutions,and ASP-based planners are better on tasks with a large number of objects or tasks in which complex reasoning is required to reason about action preconditions and effects. The resulting analysis can inform selection among general-purpose planning systems for particular robot task planning domains.展开更多
Building upon prior research that highlighted the need for standardizing environments for building controlresearch, and inspired by recently introduced challenges for real life reinforcement learning (RL) control, her...Building upon prior research that highlighted the need for standardizing environments for building controlresearch, and inspired by recently introduced challenges for real life reinforcement learning (RL) control, herewe propose a non-exhaustive set of nine real world challenges for RL control in grid-interactive buildings(GIBs). We argue that research in this area should be expressed in this framework in addition to providing astandardized environment for repeatability. Advanced controllers such as model predictive control (MPC) andRL control have both advantages and disadvantages that prevent them from being implemented in real worldproblems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we caninvestigate the performance of the controllers under a variety of situations and generate a fair comparison.展开更多
基金supported in part by NSF (IIS1637736, IIS-1651089, IIS-1724157)ONR (N00014-182243)+2 种基金FLI (RFP2-000)Intel, RaytheonLockheed Martin
文摘Robots need task planning algorithms to sequence actions toward accomplishing goals that are impossible through individual actions. Off-the-shelf task planners can be used by intelligent robotics practitioners to solve a variety of planning problems. However, many different planners exist, each with different strengths and weaknesses,and there are no general rules for which planner would be best to apply to a given problem. In this study, we empirically compare the performance of state-of-the-art planners that use either the planning domain description language(PDDL) or answer set programming(ASP) as the underlying action language. PDDL is designed for task planning, and PDDL-based planners are widely used for a variety of planning problems. ASP is designed for knowledge-intensive reasoning, but can also be used to solve task planning problems. Given domain encodings that are as similar as possible, we find that PDDL-based planners perform better on problems with longer solutions,and ASP-based planners are better on tasks with a large number of objects or tasks in which complex reasoning is required to reason about action preconditions and effects. The resulting analysis can inform selection among general-purpose planning systems for particular robot task planning domains.
文摘Building upon prior research that highlighted the need for standardizing environments for building controlresearch, and inspired by recently introduced challenges for real life reinforcement learning (RL) control, herewe propose a non-exhaustive set of nine real world challenges for RL control in grid-interactive buildings(GIBs). We argue that research in this area should be expressed in this framework in addition to providing astandardized environment for repeatability. Advanced controllers such as model predictive control (MPC) andRL control have both advantages and disadvantages that prevent them from being implemented in real worldproblems. Comparisons between the two are rare, and often biased. By focusing on the challenges, we caninvestigate the performance of the controllers under a variety of situations and generate a fair comparison.
