Symbolic Planning Research Articles

A regrasp planning component for object reorientation

This paper presents a regrasp planning component for object reorientation. It includes a grasp planner, a placement planner, and a regrasp sequence solver. Given the initial and goal poses of an object, the regrasp planning component finds a sequence of robot postures and grasp configurations that reorient the object from the initial pose to the goal. The regrasp planning component works as a mid-level connector in the whole planning system for object reorientation. It is open to low-level motion planning algorithms by providing two end-effector poses as the input. It is also open to high-level assembly or symbolic planners by providing pick-and-place predicates. The proposed component is demonstrated with several simulation examples and real-robot executions using a Kawada Hiro robot and Robotiq 85 grippers.

Planning Robust Manual Tasks in Hierarchical Belief Spaces

This paper introduces a technique for planning in hierarchical belief spaces and demonstrates the idea in an autonomous assembly task. The objective is to effectively propagate belief across multiple levels of abstraction to make control decisions that expose useful state information, manage uncertainty and risk, and actively satisfy task specifications. This approach is demonstrated by performing multiple instances of a simple class of assembly tasks using the uBot-6 mobile manipulator with a two-level hierarchy that manages uncertainty over objects and assembly geometry. The result is a method for composing a sequence of manual interactions that causes changes to the environment and exposes new information in order to support belief that the task is satisfied. This approach has the added virtue that it provides a natural way to accomplish tasks while simultaneously suppressing errors and mitigating risk. We compare performance in an example assembly task against a baseline hybrid approach that combines uncertainty management with a symbolic planner and show statistically significant improvement in task outcomes. In additional demonstrations that challenge the system we highlight useful artifacts of the approach---risk management and autonomous recovery from unexpected events.

Symbolic Planning with Edge-Valued Multi-Valued Decision Diagrams

Symbolic representations have attracted significant attention in optimal planning. Binary Decision Diagrams (BDDs) form the basis for symbolic search algorithms. Closely related are Algebraic Decision Diagrams (ADDs), used to represent heuristic functions. Also, progress was made in dealing with models that take state-dependent action costs into account. Here, costs are represented as Edge-valued Multi-valued Decision Diagrams (EVMDDs), which can be exponentially more compact than the corresponding ADD representation. However, they were not yet considered for symbolic planning. In this work, we study EVMDD-based symbolic search for optimal planning. We define EVMDD-based representations of state sets and transition relations, and show how to compute the necessary operations required for EVMDD-A*. This EVMDD-based version of symbolic A* generalizes its BDD variant, and allows to solve planning tasks with state-dependent action costs. We prove theoretically that our approach is sound, complete and optimal. Additionally, we present an empirical analysis comparing EVMDD-A* to BDD-A* and explicit A* search. Our results underscore the usefulness of symbolic approaches and the feasibility of dealing with models that go beyond unit costs.

FFRob: Leveraging symbolic planning for efficient task and motion planning

Mobile manipulation problems involving many objects are challenging to solve due to the high dimensionality and multi-modality of their hybrid configuration spaces. Planners that perform a purely geometric search are prohibitively slow for solving these problems because they are unable to factor the configuration space. Symbolic task planners can efficiently construct plans involving many variables but cannot represent the geometric and kinematic constraints required in manipulation. We present the FFRob algorithm for solving task and motion planning problems. First, we introduce extended action specification (EAS) as a general purpose planning representation that supports arbitrary predicates as conditions. We adapt existing heuristic search ideas for solving strips planning problems, particularly delete-relaxations, to solve EAS problem instances. We then apply the EAS representation and planners to manipulation problems resulting in FFRob. FFRob iteratively discretizes task and motion planning problems using batch sampling of manipulation primitives and a multi-query roadmap structure that can be conditionalized to evaluate reachability under different placements of movable objects. This structure enables the EAS planner to efficiently compute heuristics that incorporate geometric and kinematic planning constraints to give a tight estimate of the distance to the goal. Additionally, we show FFRob is probabilistically complete and has a finite expected runtime. Finally, we empirically demonstrate FFRob’s effectiveness on complex and diverse task and motion planning tasks including rearrangement planning and navigation among movable objects.

Integrating multi-purpose natural language understanding, robot’s memory, and symbolic planning for task execution in humanoid robots

Abstract We propose an approach for instructing a robot using natural language to solve complex tasks in a dynamic environment. In this study, we elaborate on a framework that allows a humanoid robot to understand natural language, derive symbolic representations of its sensorimotor experience, generate complex plans according to the current world state, and monitor plan execution. The presented development supports replacing missing objects and suggesting possible object locations. It is a realization of the concept of structural bootstrapping developed in the context of the European project Xperience. The framework is implemented within the robot development environment ArmarX. We evaluate the framework on the humanoid robot ARMAR-III in the context of two experiments: a demonstration of the real execution of a complex task in the kitchen environment on ARMAR-III and an experiment with untrained users in a simulation environment.

Hybrid Task Planning Grounded in Belief: Constructing Physical Copies of Simple Structures

Symbolic planning methods have proved to be challenging in robotics due to partial observability and noise as well as unavoidable exceptions to rules that symbol semantics depend on. Often the symbols that a robot considers to support for planning are brittle, making them unsuited for even relatively short term use. Maturing probabilistic methods in robotics, however, are providing a sound basis for symbol grounding that supports using probabilistic distributions over symbolic entities as the basis for planning. In this paper, we describe a belief-space planner that stabilizes the semantics of feedback from the environment by actively interacting with a scene. When distributions over higher-level abstractions stabilize, powerful symbolic planning techniques can provide reliable guidance for problem solving. We present such an approach in a hybrid planning scheme that actively controls uncertainty and yields robust state estimation with bounds on uncertainty that can make effective use of powerful symbolic planning techniques. We illustrate the idea in a hybrid planner for autonomous construction tasks with a real robot system.

Play in natural environments: A pilot study quantifying the behavior of children on playground equipment

ABSTRACTPlayground design is critical to school-based practice, insuring access and use for all children. The play behavior of children with special needs is qualitatively and quantitatively different than their typically developing peers. However, empirical data is needed to support the therapeutic value of playground equipment used with school-aged children. Thirty-two hours of videotape was collected from 140 children who were typically developing (male = 56%) and 41 children with a variety of developmental disabilities including autism, ADHD, sensory and regulatory disorders (male = 76%), ages 3 to 15 years. Six pieces of playground equipment were analyzed using a behavioral coding system for sensory features, social interaction, self-regulation, motor skills, and play levels. Content validity of the behavioral coding scheme was obtained through a case study. Proprioception was enhanced through active use of the playground equipment. Increased verbalizations and positive affect were observed across all pieces of equipment. Symbolic play, novel use and motor planning were fostered. Regaining regulation and expressions of self-esteem were quantifiable. Correlations support relations between proprioception and social interaction; positive affect and social interaction; motor planning and self-esteem; and play levels with positive affect and social interaction. Improvements in regaining regulation, self-esteem, and postive affect were demonstrated through the case study analyses. Playground behaviors could be described using a behavioral coding scheme that includes sensory features, social interaction, self-regulation, motor skills, and play levels. This behavioral coding system validated the features of an inclusive playground and quantified the effectiveness of intervention.

Architecture for the Automatic Generation of Plans for Multiple UAS from a Generic Mission Description

A planning approach for a platform composed of multiple unmanned aerial systems is presented in this paper. The research activities are focused on the interoperability, task allocation and task planning problems within the system. In order to tackle with the interoperability problem between the vehicles of the platform and other external systems, C-BML has been chosen as the standard language to formalize the description of the missions. Regarding the planning problems involved, several planners have been applied to solve them: a task allocation planner to create an initial assignment of tasks to vehicles, a symbolic planner for high-level reasoning and tools for geometric reasoning. The main contribution of the paper is the use of consolidated task planning techniques to automatically generate low-level plans from a mission described in C-BML, filling the gap between interoperability and automatic plan generation for missions where multiple heterogeneous aerial platforms are involved. The approach has been tested in missions involving multiple surveillance and 3D map generation tasks and the paper includes experimental results.

Robot Task Planning in Deterministic and Probabilistic Conditions Using Semantic Knowledge Base

A new method is proposed to increase the reliability of generating symbolic plans by extending the Semantic-Knowledge Based (SKB) plan generation to take into account the amount of information and uncertainty related to existing objects, their types and properties, as well as their relationships with each other. This approach constructs plans by depending on probabilistic values which are derived from learning statistical relational models such as Markov Logic Networks (MLN). An MLN module is established for probabilistic learning and inference together with semantic information to provide a basis for plausible learning and reasoning services in support of robot task-planning. The MLN module is constructed by using an algorithm to transform the knowledge stored in SKB to types, predicates and formulas which represent the main building block for this module. Following this, the semantic domain knowledge is used to derive implicit expectations of world states and the effects of the action which is nominated for insertion into the task plan. The expectations are matched with MLN output.

<b>Architectures of a fragmented memory: imprisonment and liberation in W. G. Sebald's <i>Austerlitz

Austerlitz (2001), written by the German author Sebald, presents a fragmented narrative with various levels of relations and symbolic plans outlined by the story of Jacques Austerlitz. This form of literary construction is in perfect harmony with the fragmentation of the past and the oblivion that shape Austerlitz. As the character’s investigations and self-discovery process advance, we find that he was one of the Jewish children brought to London by the Kindertransports on the eve of World War II. In this study, we investigate a kind of dividing line in Austerlitz’s story, establishing itself as an ‘in-between’ that evokes two considerably distinct moments of the narrative. These moments sometimes evoke imprisonment and relate to imprisoned memories, and sometimes evoke liberation and relate to freed memory. First, we track images and descriptions that refer to imprisonment when Austerlitz feels trapped, isolated, without past or memories. Subsequently, we map descriptions of this kind of liberation that begins when the character starts to redraw his past, in a process of self-discovery and reconstruction of his story and his identity. In this work, both Austerlitz and Sebald evoke the need to remember the traumatic past and witness it, despite all the pain and incomprehension while facing it.

A Novel Cost Estimation Approach for Wood Harvesting Operations Using Symbolic Planning

Abstract While forestry is an important economic factor, the methods commonly used to estimate potential financial gains from undertaking a harvesting operation are usually based on heuristics and experience. Those methods use an abstract view on the harvesting project at hand, focusing on a few general statistical parameters. To improve the accuracy of felling cost estimates, we propose a novel, single-tree-based cost estimation approach, which utilizes knowledge about the harvesting operation at hand to allow for a more specific and accurate estimate of felling costs. The approach utilizes well-known symbolic planning algorithms which are interfaced via the Planning Domain Definition Language (PDDL) and compile work orders. The work orders can then be used to estimate the total working time and thus the estimated cost for an individual harvesting project, as well as some additional efficiency statistics. Since a large proportion of today's harvesting operations are mechanized instead of motor manual, we focus on the planning of harvester and forwarder workflows. However, the use of these heavy forest machines carries the risk of damaging forest soil when repeatedly driving along skidding roads. Our approach readily allows for assessment of these risks.

Symbolic planning and control using game theory and grammatical inference

A system can accomplish an objective specified in temporal logic while interacting with an unknown, dynamic but rule-governed environment, by employing grammatical inference and adapting its plan of action on-line. The purposeful interaction of the system with its unknown environment can be described by a deterministic two-player zero-sum game. Using special new product operations, the whole game can be expressed with a factored, modular representation. This representation not only offers computational benefits but also isolates the unknown behavior of the dynamic environment in a particular subsystem, which then becomes the target of learning. As the fidelity of the identified environment model increases, the strategy synthesized based on the learned hypothesis converges in finite time to the one that satisfies the task specification.

Directed Fixed-Point Regression-Based Planning for Non-Deterministic Domains

We present a novel approach to fully-observable nondeterministic planning (FOND) that attempts to bridge the gap between symbolic fix-point computation and recent approaches based on forward heuristic search. Concretely, we formalize the relationship between symbolic and dynamic programming nondeterministic planners, and then exploit such connection to propose a novel familyof planning algorithms that reasons over symbolic policies in a directed manner. By doing so, our proposal reasons over sets of states and executions in a succinct way (as done by symbolic planners) while biasing the reasoning with respect to the initial and goal states of the specific planning problem at hand (as done by heuristic planners). We show empirical results that prove this approach promising in settings where there is an intrinsic tension between plan efficiency and plan "robustness," a feature to be expected in nondeterministic domains.

An Approach for Efficient Planning of Robotic Manipulation Tasks

Robot manipulation is a challenging task for planning as itinvolves a mixture of symbolic planning and geometric plan-ning. We would like to express goals and many action ef-fects symbolically, for example specifying a goal such as forall x, if x is a cup, then x should be on the tray, but to ac-complish this we may need to plan the geometry of fitting allthe cups on the tray and how to grasp, move and release thecups to achieve that geometry. In the ideal case, this couldbe accomplished by a fully hybrid planner that alternates be-tween geometric and symbolic reasoning to generate a solu-tion. However, in practice this is very complex, and the fullpower of this approach may only be required for a small sub-set of problems. Instead, we plan completely symbolically,and then attempt to generate a geometric plan by translatingthe symoblic predicates into geometric relationships. We thenexecute this plan in simulation, and if it fails, we backtrack,first in geometric space, and then if necessary in symbolic.We show that this approach, while not complete, solves anumber of challenging manipulation problems, and demon-strate it running on a robotic platform.

Transition Trees for Cost-Optimal Symbolic Planning

Symbolic search with binary decision diagrams (BDDs) often saves huge amounts of memory and computation time. In this paper we propose two general techniques based on transition relation trees to advance BDD search by refining the image operator to compute the set of successors. First, the conjunction tree selects the set of applicable actions through filtering their precondition. Then, the disjunction tree combines each transition result. Transition trees are used to combine several transition relations, speeding up BDD search. Experiments with bidirectional symbolic blind and symbolic A* search on planning benchmarks are reported showing good performance on most IPC 2011 domains.

Coordinating heterogeneous teams of robots using temporal symbolic planning

The efficient coordination of a team of heterogeneous robots is an important requirement for exploration, rescue, and disaster recovery missions. In this paper, we present a novel approach to target assignment for heterogeneous teams of robots. It goes beyond existing target assignment algorithms in that it explicitly takes symbolic actions into account. Such actions include the deployment and retrieval of other robots or manipulation tasks. Our method integrates a temporal planning approach with a traditional cost-based planner. The proposed approach was implemented and evaluated in two distinct settings. First, we coordinated teams of marsupial robots. Such robots are able to deploy and pickup smaller robots. Second, we simulated a disaster scenario where the task is to clear blockades and reach certain critical locations in the environment. A similar setting was also investigated using a team of real robots. The results show that our approach outperforms ad-hoc extensions of state-of-the-art cost-based coordination methods and that the approach is able to efficiently coordinate teams of heterogeneous robots and to consider symbolic actions.

Integrating Robot Task Planner with Common-sense Knowledge Base to Improve the Efficiency of Planning

This paper presents a developed approach for intelligently generating symbolic plans by mobile robots acting in domestic environments, such as offices and houses. The significance of the approach lies in developing a new framework that consists of the new modeling of high-level robot actions and then their integration with common-sense knowledge in order to support a robotic task planner. This framework will enable interactions between the task planner and the semantic knowledge base directly. By using common-sense domain knowledge, the task planner will take into consideration the properties and relations of objects and places in its environment, before creating semantically related actions that will represent a plan. This plan will accomplish the user order. The robot task planner will use the available domain knowledge to check the next related actions to the current one and the action's conditions met will be chosen. Then the robot will use the immediately available knowledge information to check whether the plan outcomes are met or violated.

Integration of Symbolic Task Planning into Operations within an Unstructured Environment

To ensure a robot capable of robust task execution in unstructured environments, task planners need to have a high-level understanding of the nature of the world, reasoning for deliberate actions, and reacting to environment changes. Proposed is a practical task planning approach that seamlessly integrating deeper domain knowledge, real time perception and symbolic planning for robot operation. A higher degree of autonomy under unstructured environment will be endowed to the robot with the proposed approach.

Learning and Reasoning with Action-Related Places for Robust Mobile Manipulation

We propose the concept of Action-Related Place (ARPlace) as a powerful and flexible representation of task-related place in the context of mobile manipulation. ARPlace represents robot base locations not as a single position, but rather as a collection of positions, each with an associated probability that the manipulation action will succeed when located there. ARPlaces are generated using a predictive model that is acquired through experience-based learning, and take into account the uncertainty the robot has about its own location and the location of the object to be manipulated. When executing the task, rather than choosing one specific goal position based only on the initial knowledge about the task context, the robot instantiates an ARPlace, and bases its decisions on this ARPlace, which is updated as new information about the task becomes available. To show the advantages of this least-commitment approach, we present a transformational planner that reasons about ARPlaces in order to optimize symbolic plans. Our empirical evaluation demonstrates that using ARPlaces leads to more robust and efficient mobile manipulation in the face of state estimation uncertainty on our simulated robot.

Multimodal Integration Processes in Plan-Based Service Robot Control

Cross-modal integration processes are essential for service robots to reliably perceive relevant parts of the partially known unstructured environment. We demonstrate how multimodal integration on different abstraction levels leads to reasonable behavior that would be difficult to achieve with unimodal approaches. Sensing and acting modalities are composed to multimodal robot skills via a fuzzy multisensor fusion approach. Single modalities constitute basic robot skills that can dynamically be composed to appropriate behavior by symbolic planning. Furthermore, multimodal integration is exploited to answer relevant queries about the partially known environment. All these approaches are successfully implemented and tested on our mobile service robot platform TASER.