We investigate the problem of synthesizing optimal control policies for Markov decision processes (MDPs) with both qualitative and quantitative objectives. Specifically, our goal is to achieve a given linear temporal logic (LTL) task with probability one, while maximizing the \emph{entropy rate} of the system. The notion of entropy rate characterizes the long-run average (un)predictability of a stochastic process. Such an optimal policy is of our interest, in particular, from the security point of view, as it not only ensures the completion of tasks, but also maximizes the unpredictability of the system. However, existing works only focus on maximizing the total entropy which may diverge to infinity for infinite horizon. In this paper, we provide a complete solution to the entropy rate maximization problem under LTL constraints. Specifically, we first present an algorithm for synthesizing entropy rate maximizing policies for communicating MDPs. Then based on a new state classification method, we show the entropy rate maximization problem under LTL task can be effectively solved in polynomial-time. We illustrate the proposed algorithm based on two case studies of robot task planning scenario.
In this paper, we investigate the problem of synthesizing controllers for temporal logic specifications under security constraint. We assume that there exists a passive intruder (eavesdropper) that can partially observe the behavior of the system. For the purpose of security, we require that the system's behaviors are unpredictable in the sense that the intruder cannot determine for sure that the system will exactly accomplish the task in $K$ steps ahead. This problem is particularly challenging since future information is involved in the synthesis process. We propose a novel information structure that predicts the effect of control in the future. A sound and complete algorithm is developed to synthesize a controller which ensures both task completion and security guarantee. The proposed approach is illustrated by a case study of robot task planning.
The functional object-oriented network (FOON) has been developed as a knowledge representation method that can be used by robots in order to perform task planning. A FOON can be observed as a graph that can provide an ordered plan for robots to retrieve a task tree, through the knowledge retrieval process. We compare two search algorithms to evaluate their performance in extracting task trees: iterative deepening search (IDS) and greedy best-first search (GBFS) with two different heuristic functions. Then, we determine which algorithm is capable of obtaining a task tree for various cooking recipes using the least number of functional units. Preliminary results show that each algorithm can perform better than the other, depending on the recipe provided to the search algorithm.
Search algorithms are applied where data retrieval with specified specifications is required. The motivation behind developing search algorithms in Functional Object-Oriented Networks is that most of the time, a certain recipe needs to be retrieved or ingredients for a certain recipe needs to be determined. According to the introduction, there is a time when execution of an entire recipe is not available for a robot thus prompting the need to retrieve a certain recipe or ingredients. With a quality FOON, robots can decipher a task goal, find the correct objects at the required states on which to operate and output a sequence of proper manipulation motions. This paper shows several proposed weighted FOON and task planning algorithms that allow a robot and a human to successfully complete complicated tasks together with higher success rates than a human doing them alone.
Flexible task planning is still a significant challenge for robots. The inability of robots to creatively adapt their task plans to new or unforeseen challenges is largely attributable to their limited understanding of their activities and the environment. Cooking, for example, requires a person to occasionally take risks that a robot would find extremely dangerous. We may obtain manipulation sequences by employing knowledge that is drawn from numerous video sources thanks to knowledge retrieval through graph search.
Robots can complete all human-performed tasks, but due to their current lack of knowledge, some tasks still cannot be completed by them with a high degree of success. However, with the right knowledge, these tasks can be completed by robots with a high degree of success, reducing the amount of human effort required to complete daily tasks. In this paper, the FOON, which describes the robot action success rate, is discussed. The functional object-oriented network (FOON) is a knowledge representation for symbolic task planning that takes the shape of a graph. It is to demonstrate the adaptability of FOON in developing a novel and adaptive method of solving a problem utilizing knowledge obtained from various sources, a graph retrieval methodology is shown to produce manipulation motion sequences from the FOON to accomplish a desired aim. The outcomes are illustrated using motion sequences created by the FOON to complete the desired objectives in a simulated environment.
To assist with everyday human activities, robots must solve complex long-horizon tasks and generalize to new settings. Recent deep reinforcement learning (RL) methods show promise in fully autonomous learning, but they struggle to reach long-term goals in large environments. On the other hand, Task and Motion Planning (TAMP) approaches excel at solving and generalizing across long-horizon tasks, thanks to their powerful state and action abstractions. But they assume predefined skill sets, which limits their real-world applications. In this work, we combine the benefits of these two paradigms and propose an integrated task planning and skill learning framework named LEAGUE (Learning and Abstraction with Guidance). LEAGUE leverages the symbolic interface of a task planner to guide RL-based skill learning and creates abstract state space to enable skill reuse. More importantly, LEAGUE learns manipulation skills in-situ of the task planning system, continuously growing its capability and the set of tasks that it can solve. We evaluate LEAGUE on four challenging simulated task domains and show that LEAGUE outperforms baselines by large margins. We also show that the learned skills can be reused to accelerate learning in new tasks domains and transfer to a physical robot platform.
A good estimation of the actions' cost is key in task planning for human-robot collaboration. The duration of an action depends on agents' capabilities and the correlation between actions performed simultaneously by the human and the robot. This paper proposes an approach to learning actions' costs and coupling between actions executed concurrently by humans and robots. We leverage the information from past executions to learn the average duration of each action and a synergy coefficient representing the effect of an action performed by the human on the duration of the action performed by the robot (and vice versa). We implement the proposed method in a simulated scenario where both agents can access the same area simultaneously. Safety measures require the robot to slow down when the human is close, denoting a bad synergy of tasks operating in the same area. We show that our approach can learn such bad couplings so that a task planner can leverage this information to find better plans.
We consider the human-aware task planning problem where a human-robot team is given a shared task with a known objective to achieve. Recent approaches tackle it by modeling it as a team of independent, rational agents, where the robot plans for both agents' (shared) tasks. However, the robot knows that humans cannot be administered like artificial agents, so it emulates and predicts the human's decisions, actions, and reactions. Based on earlier approaches, we describe a novel approach to solve such problems, which models and uses execution-time observability conventions. Abstractly, this modeling is based on situation assessment, which helps our approach capture the evolution of individual agents' beliefs and anticipate belief divergences that arise in practice. It decides if and when belief alignment is needed and achieves it with communication. These changes improve the solver's performance: (a) communication is effectively used, and (b) robust for more realistic and challenging problems.
Automated task planning algorithms have been developed to help robots complete complex tasks that require multiple actions. Most of those algorithms have been developed for "closed worlds" assuming complete world knowledge is provided. However, the real world is generally open, and the robots frequently encounter unforeseen situations that can potentially break the planner's completeness. This paper introduces a novel algorithm (COWP) for open-world task planning and situation handling that dynamically augments the robot's action knowledge with task-oriented common sense. In particular, common sense is extracted from Large Language Models based on the current task at hand and robot skills. For systematic evaluations, we collected a dataset that includes 561 execution-time situations in a dining domain, where each situation corresponds to a state instance of a robot being potentially unable to complete a task using a solution that normally works. Experimental results show that our approach significantly outperforms competitive baselines from the literature in the success rate of service tasks. Additionally, we have demonstrated COWP using a mobile manipulator. The project website is available at: https://cowplanning.github.io/, where a more detailed version can also be found. This version has been accepted for publication in Autonomous Robots.
Task planning can require defining myriad domain knowledge about the world in which a robot needs to act. To ameliorate that effort, large language models (LLMs) can be used to score potential next actions during task planning, and even generate action sequences directly, given an instruction in natural language with no additional domain information. However, such methods either require enumerating all possible next steps for scoring, or generate free-form text that may contain actions not possible on a given robot in its current context. We present a programmatic LLM prompt structure that enables plan generation functional across situated environments, robot capabilities, and tasks. Our key insight is to prompt the LLM with program-like specifications of the available actions and objects in an environment, as well as with example programs that can be executed. We make concrete recommendations about prompt structure and generation constraints through ablation experiments, demonstrate state of the art success rates in VirtualHome household tasks, and deploy our method on a physical robot arm for tabletop tasks. Website at progprompt.github.io
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are limited by the lack of grounding in the surrounding scene. In this paper, we develop NLMap, an open-vocabulary and queryable scene representation to address this problem. NLMap serves as a framework to gather and integrate contextual information into LLM planners, allowing them to see and query available objects in the scene before generating a context-conditioned plan. NLMap first establishes a natural language queryable scene representation with Visual Language models (VLMs). An LLM based object proposal module parses instructions and proposes involved objects to query the scene representation for object availability and location. An LLM planner then plans with such information about the scene. NLMap allows robots to operate without a fixed list of objects nor executable options, enabling real robot operation unachievable by previous methods. Project website: https://nlmap-saycan.github.io
Goal-oriented generative script learning aims to generate subsequent steps to reach a particular goal, which is an essential task to assist robots or humans in performing stereotypical activities. An important aspect of this process is the ability to capture historical states visually, which provides detailed information that is not covered by text and will guide subsequent steps. Therefore, we propose a new task, Multimedia Generative Script Learning, to generate subsequent steps by tracking historical states in both text and vision modalities, as well as presenting the first benchmark containing 5,652 tasks and 79,089 multimedia steps. This task is challenging in three aspects: the multimedia challenge of capturing the visual states in images, the induction challenge of performing unseen tasks, and the diversity challenge of covering different information in individual steps. We propose to encode visual state changes through a selective multimedia encoder to address the multimedia challenge, transfer knowledge from previously observed tasks using a retrieval-augmented decoder to overcome the induction challenge, and further present distinct information at each step by optimizing a diversity-oriented contrastive learning objective. We define metrics to evaluate both generation and inductive quality. Experiment results demonstrate that our approach significantly outperforms strong baselines.
We investigate the problem of coordinating two robot arms to solve non-monotone tabletop multi-object rearrangement tasks. In a non-monotone rearrangement task, complex object-object dependencies exist that require moving some objects multiple times to solve an instance. In working with two arms in a large workspace, some objects must be handed off between the robots, which further complicates the planning process. For the challenging dual-arm tabletop rearrangement problem, we develop effective task planning algorithms for scheduling the pick-n-place sequence that can be properly distributed between the two arms. We show that, even without using a sophisticated motion planner, our method achieves significant time savings in comparison to greedy approaches and naive parallelization of single-robot plans.
Following work on joint object-action representations, functional object-oriented networks (FOON) were introduced as a knowledge graph representation for robots. A FOON contains symbolic concepts useful to a robot's understanding of tasks and its environment for object-level planning. Prior to this work, little has been done to show how plans acquired from FOON can be executed by a robot, as the concepts in a FOON are too abstract for execution. We thereby introduce the idea of exploiting object-level knowledge as a FOON for task planning and execution. Our approach automatically transforms FOON into PDDL and leverages off-the-shelf planners, action contexts, and robot skills in a hierarchical planning pipeline to generate executable task plans. We demonstrate our entire approach on long-horizon tasks in CoppeliaSim and show how learned action contexts can be extended to never-before-seen scenarios.
3D scene graphs (3DSGs) are an emerging description; unifying symbolic, topological, and metric scene representations. However, typical 3DSGs contain hundreds of objects and symbols even for small environments; rendering task planning on the full graph impractical. We construct TASKOGRAPHY, the first large-scale robotic task planning benchmark over 3DSGs. While most benchmarking efforts in this area focus on vision-based planning, we systematically study symbolic planning, to decouple planning performance from visual representation learning. We observe that, among existing methods, neither classical nor learning-based planners are capable of real-time planning over full 3DSGs. Enabling real-time planning demands progress on both (a) sparsifying 3DSGs for tractable planning and (b) designing planners that better exploit 3DSG hierarchies. Towards the former goal, we propose SCRUB, a task-conditioned 3DSG sparsification method; enabling classical planners to match and in some cases surpass state-of-the-art learning-based planners. Towards the latter goal, we propose SEEK, a procedure enabling learning-based planners to exploit 3DSG structure, reducing the number of replanning queries required by current best approaches by an order of magnitude. We will open-source all code and baselines to spur further research along the intersections of robot task planning, learning and 3DSGs.
We devise a 3D scene graph representation, contact graph+ (cg+), for efficient sequential task planning. Augmented with predicate-like attributes, this contact graph-based representation abstracts scene layouts with succinct geometric information and valid robot-scene interactions. Goal configurations, naturally specified on contact graphs, can be produced by a genetic algorithm with a stochastic optimization method. A task plan is then initialized by computing the Graph Editing Distance (GED) between the initial contact graphs and the goal configurations, which generates graph edit operations corresponding to possible robot actions. We finalize the task plan by imposing constraints to regulate the temporal feasibility of graph edit operations, ensuring valid task and motion correspondences. In a series of simulations and experiments, robots successfully complete complex sequential object rearrangement tasks that are difficult to specify using conventional planning language like Planning Domain Definition Language (PDDL), demonstrating the high feasibility and potential of robot sequential task planning on contact graph.
We develop an algorithm for the motion and task planning of a system comprised of multiple robots and unactuated objects under tasks expressed as Linear Temporal Logic (LTL) constraints. The robots and objects evolve subject to uncertain dynamics in an obstacle-cluttered environment. The key part of the proposed solution is the intelligent construction of a coupled transition system that encodes the motion and tasks of the robots and the objects. We achieve such a construction by designing appropriate adaptive control protocols in the lower level, which guarantee the safe robot navigation/object transportation in the environment while compensating for the dynamic uncertainties. The transition system is efficiently interfaced with the temporal logic specification via a sampling-based algorithm to output a discrete path as a sequence of synchronized actions of the robots; such actions satisfy the robots' as well as the objects' specifications. The robots execute this discrete path by using the derived low level control protocol. Simulation results verify the proposed framework.
Real-world deployment of new technology and capabilities can be daunting. The recent DARPA Subterranean (SubT) Challenge, for instance, aimed at the advancement of robotic platforms and autonomy capabilities in three one-year development pushes. While multi-agent systems are traditionally deployed in controlled and structured environments that allow for controlled testing (e.g., warehouses), the SubT challenge targeted various types of unknown underground environments that imposed the risk of robot loss in the case of failure. In this work, we introduce a video game-inspired interface, an autonomous mission assistant, and test and deploy these using a heterogeneous multi-agent system in challenging environments. This work leads to improved human-supervisory control for a multi-agent system reducing overhead from application switching, task planning, execution, and verification while increasing available exploration time with this human-autonomy teaming platform.
Intuitive and efficient physical human-robot collaboration relies on the mutual observability of the human and the robot, i.e. the two entities being able to interpret each other's intentions and actions. This is remedied by a myriad of methods involving human sensing or intention decoding, as well as human-robot turn-taking and sequential task planning. However, the physical interaction establishes a rich channel of communication through forces, torques and haptics in general, which is often overlooked in industrial implementations of human-robot interaction. In this work, we investigate the role of haptics in human collaborative physical tasks, to identify how to integrate physical communication in human-robot teams. We present a task to balance a ball at a target position on a board either bimanually by one participant, or dyadically by two participants, with and without haptic information. The task requires that the two sides coordinate with each other, in real-time, to balance the ball at the target. We found that with training the completion time and number of velocity peaks of the ball decreased, and that participants gradually became consistent in their braking strategy. Moreover we found that the presence of haptic information improved the performance (decreased completion time) and led to an increase in overall cooperative movements. Overall, our results show that humans can better coordinate with one another when haptic feedback is available. These results also highlight the likely importance of haptic communication in human-robot physical interaction, both as a tool to infer human intentions and to make the robot behaviour interpretable to humans.