One of the main challenges of advancing task-oriented learning such as visual task planning and reinforcement learning is the lack of realistic and standardized environments for training and testing AI agents. Previously, researchers often relied on ad-hoc lab environments. There have been recent advances in virtual systems built with 3D physics engines and photo-realistic rendering for indoor and outdoor environments, but the embodied agents in those systems can only conduct simple interactions with the world (e.g., walking around, moving objects, etc.). Most of the existing systems also do not allow human participation in their simulated environments. In this work, we design and implement a virtual reality (VR) system, VRKitchen, with integrated functions which i) enable embodied agents powered by modern AI methods (e.g., planning, reinforcement learning, etc.) to perform complex tasks involving a wide range of fine-grained object manipulations in a realistic environment, and ii) allow human teachers to perform demonstrations to train agents (i.e., learning from demonstration). We also provide standardized evaluation benchmarks and data collection tools to facilitate a broad use in research on task-oriented learning and beyond.
In this report, we introduce an artificial dataset generator for Photo-realistic Blocksworld domain. Blocksworld is one of the oldest high-level task planning domain that is well defined but contains sufficient complexity, e.g., the conflicting subgoals and the decomposability into subproblems. We aim to make this dataset a benchmark for Neural-Symbolic integrated systems and accelerate the research in this area. The key advantage of such systems is the ability to obtain a symbolic model from the real-world input and perform a fast, systematic, complete algorithm for symbolic reasoning, without any supervision and the reward signal from the environment.
Task-motion planning (TMP) addresses the problem of efficiently generating executable and low-cost task plans in a discrete space such that the (initially unknown) action costs are determined by motion plans in a corresponding continuous space. However, a task-motion plan can be sensitive to unexpected domain uncertainty and changes, leading to suboptimal behaviors or execution failures. In this paper, we propose a novel framework, TMP-RL, which is an integration of TMP and reinforcement learning (RL) from the execution experience, to solve the problem of robust task-motion planning in dynamic and uncertain domains. TMP-RL features two nested planning-learning loops. In the inner TMP loop, the robot generates a low-cost, feasible task-motion plan by iteratively planning in the discrete space and updating relevant action costs evaluated by the motion planner in continuous space. In the outer loop, the plan is executed, and the robot learns from the execution experience via model-free RL, to further improve its task-motion plans. RL in the outer loop is more accurate to the current domain but also more expensive, and using less costly task and motion planning leads to a jump-start for learning in the real world. Our approach is evaluated on a mobile service robot conducting navigation tasks in an office area. Results show that TMP-RL approach significantly improves adaptability and robustness (in comparison to TMP methods) and leads to rapid convergence (in comparison to task planning (TP)-RL methods). We also show that TMP-RL can reuse learned values to smoothly adapt to new scenarios during long-term deployments.
Planetary exploration missions with Mars rovers are complicated, which generally require elaborated task planning by human experts, from the path to take to the images to capture. NASA has been using this process to acquire over 22 million images from the planet Mars. In order to improve the degree of automation and thus efficiency in this process, we propose a system for planetary rovers to actively search for prominence of prespecified scientific features in captured images. Scientists can prespecify such search tasks in natural language and upload them to a rover, on which the deployed system constantly captions captured images with a deep image captioning network and compare the auto-generated captions to the prespecified search tasks by certain metrics so as to prioritize those images for transmission. As a beneficial side effect, the proposed system can also be deployed to ground-based planetary data systems as a content-based search engine.
This paper focuses on semantic task planning, i.e., predicting a sequence of actions toward accomplishing a specific task under a certain scene, which is a new problem in computer vision research. The primary challenges are how to model task-specific knowledge and how to integrate this knowledge into the learning procedure. In this work, we propose training a recurrent long short-term memory (LSTM) network to address this problem, i.e., taking a scene image (including pre-located objects) and the specified task as input and recurrently predicting action sequences. However, training such a network generally requires large numbers of annotated samples to cover the semantic space (e.g., diverse action decomposition and ordering). To overcome this issue, we introduce a knowledge and-or graph (AOG) for task description, which hierarchically represents a task as atomic actions. With this AOG representation, we can produce many valid samples (i.e., action sequences according to common sense) by training another auxiliary LSTM network with a small set of annotated samples. Furthermore, these generated samples (i.e., task-oriented action sequences) effectively facilitate training of the model for semantic task planning. In our experiments, we create a new dataset that contains diverse daily tasks and extensively evaluate the effectiveness of our approach.
Robotic systems, working together as a team, are becoming valuable players in different real-world applications, from disaster response to warehouse fulfillment services. Centralized solutions for coordinating multi-robot teams often suffer from poor scalability and vulnerability to communication disruptions. This paper develops a decentralized multi-agent task allocation (Dec-MATA) algorithm for multi-robot applications. The task planning problem is posed as a maximum-weighted matching of a bipartite graph, the solution of which using the blossom algorithm allows each robot to autonomously identify the optimal sequence of tasks it should undertake. The graph weights are determined based on a soft clustering process, which also plays a problem decomposition role seeking to reduce the complexity of the individual-agents' task assignment problems. To evaluate the new Dec-MATA algorithm, a series of case studies (of varying complexity) are performed, with tasks being distributed randomly over an observable 2D environment. A centralized approach, based on a state-of-the-art MILP formulation of the multi-Traveling Salesman problem is used for comparative analysis. While getting within 7-28% of the optimal cost obtained by the centralized algorithm, the Dec-MATA algorithm is found to be 1-3 orders of magnitude faster and minimally sensitive to task-to-robot ratios, unlike the centralized algorithm.
We present a general constraint-based encoding for domain-independent task planning. Task planning is characterized by causal relationships expressed as conditions and effects of optional actions. Possible actions are typically represented by templates, where each template can be instantiated into a number of primitive actions. While most previous work for domain-independent task planning has focused on primitive actions in a state-oriented view, our encoding uses a fully lifted representation at the level of action templates. It follows a time-oriented view in the spirit of previous work in constraint-based scheduling. As a result, the proposed encoding is simple and compact as it grows with the number of actions in a solution plan rather than the number of possible primitive actions. When solved with an SMT solver, we show that the proposed encoding is slightly more efficient than state-of-the-art methods on temporally constrained planning benchmarks while clearly outperforming other fully constraint-based approaches.
Smart factories are on the verge of becoming the new industrial paradigm, wherein optimization permeates all aspects of production, from concept generation to sales. To fully pursue this paradigm, flexibility in the production means as well as in their timely organization is of paramount importance. AI is planning a major role in this transition, but the scenarios encountered in practice might be challenging for current tools. Task planning is one example where AI enables more efficient and flexible operation through an online automated adaptation and rescheduling of the activities to cope with new operational constraints and demands. In this paper we present SMarTplan, a task planner specifically conceived to deal with real-world scenarios in the emerging smart factory paradigm. Including both special-purpose and general-purpose algorithms, SMarTplan is based on current automated reasoning technology and it is designed to tackle complex application domains. In particular, we show its effectiveness on a logistic scenario, by comparing its specialized version with the general purpose one, and extending the comparison to other state-of-the-art task planners.
In this paper we present an interface between a symbolic planner and a geometric task planner, which is different to a standard trajectory planner in that the former is able to perform geometric reasoning on abstract entities---tasks. We believe that this approach facilitates a more principled interface to symbolic planning, while also leaving more room for the geometric planner to make independent decisions. We show how the two planners could be interfaced, and how their planning and backtracking could be interleaved. We also provide insights for a methodology for using the combined system, and experimental results to use as a benchmark with future extensions to both the combined system, as well as to the geometric task planner.
We provide a systematic analysis of levels of integration between discrete high-level reasoning and continuous low-level reasoning to address hybrid planning problems in robotics. We identify four distinct strategies for such an integration: (i) low-level checks are done for all possible cases in advance and then this information is used during plan generation, (ii) low-level checks are done exactly when they are needed during the search for a plan, (iii) first all plans are computed and then infeasible ones are filtered, and (iv) by means of replanning, after finding a plan, low-level checks identify whether it is infeasible or not; if it is infeasible, a new plan is computed considering the results of previous low- level checks. We perform experiments on hybrid planning problems in robotic manipulation and legged locomotion domains considering these four methods of integration, as well as some of their combinations. We analyze the usefulness of levels of integration in these domains, both from the point of view of computational efficiency (in time and space) and from the point of view of plan quality relative to its feasibility. We discuss advantages and disadvantages of each strategy in the light of experimental results and provide some guidelines on choosing proper strategies for a given domain.
Intelligent robots and machines are becoming pervasive in human populated environments. A desirable capability of these agents is to respond to goal-oriented commands by autonomously constructing task plans. However, such autonomy can add significant cognitive load and potentially introduce safety risks to humans when agents behave unexpectedly. Hence, for such agents to be helpful, one important requirement is for them to synthesize plans that can be easily understood by humans. While there exists previous work that studied socially acceptable robots that interact with humans in "natural ways", and work that investigated legible motion planning, there lacks a general solution for high level task planning. To address this issue, we introduce the notions of plan {\it explicability} and {\it predictability}. To compute these measures, first, we postulate that humans understand agent plans by associating abstract tasks with agent actions, which can be considered as a labeling process. We learn the labeling scheme of humans for agent plans from training examples using conditional random fields (CRFs). Then, we use the learned model to label a new plan to compute its explicability and predictability. These measures can be used by agents to proactively choose or directly synthesize plans that are more explicable and predictable to humans. We provide evaluations on a synthetic domain and with human subjects using physical robots to show the effectiveness of our approach
Prospection is an important part of how humans come up with new task plans, but has not been explored in depth in robotics. Predicting multiple task-level is a challenging problem that involves capturing both task semantics and continuous variability over the state of the world. Ideally, we would combine the ability of machine learning to leverage big data for learning the semantics of a task, while using techniques from task planning to reliably generalize to new environment. In this work, we propose a method for learning a model encoding just such a representation for task planning. We learn a neural net that encodes the $k$ most likely outcomes from high level actions from a given world. Our approach creates comprehensible task plans that allow us to predict changes to the environment many time steps into the future. We demonstrate this approach via application to a stacking task in a cluttered environment, where the robot must select between different colored blocks while avoiding obstacles, in order to perform a task. We also show results on a simple navigation task. Our algorithm generates realistic image and pose predictions at multiple points in a given task.
Human aware planning requires an agent to be aware of the intentions, capabilities and mental model of the human in the loop during its decision process. This can involve generating plans that are explicable to a human observer as well as the ability to provide explanations when such plans cannot be generated. This has led to the notion "multi-model planning" which aim to incorporate effects of human expectation in the deliberative process of a planner - either in the form of explicable task planning or explanations produced thereof. In this paper, we bring these two concepts together and show how a planner can account for both these needs and achieve a trade-off during the plan generation process itself by means of a model-space search method MEGA. This in effect provides a comprehensive perspective of what it means for a decision making agent to be "human-aware" by bringing together existing principles of planning under the umbrella of a single plan generation process. We situate our discussion specifically keeping in mind the recent work on explicable planning and explanation generation, and illustrate these concepts in modified versions of two well known planning domains, as well as a demonstration on a robot involved in a typical search and reconnaissance task with an external supervisor.
The study of human-robot interaction is fundamental to the design and use of robotics in real-world applications. Robots will need to predict and adapt to the actions of human collaborators in order to achieve good performance and improve safety and end-user adoption. This paper evaluates a human-robot collaboration scheme that combines the task allocation and motion levels of reasoning: the robotic agent uses Bayesian inference to predict the next goal of its human partner from his or her ongoing motion, and re-plans its own actions in real time. This anticipative adaptation is desirable in many practical scenarios, where humans are unable or unwilling to take on the cognitive overhead required to explicitly communicate their intent to the robot. A behavioral experiment indicates that the combination of goal inference and dynamic task planning significantly improves both objective and perceived performance of the human-robot team. Participants were highly sensitive to the differences between robot behaviors, preferring to work with a robot that adapted to their actions over one that did not.
We present Flipper, a natural language interface for describing high-level task specifications for robots that are compiled into robot actions. Flipper starts with a formal core language for task planning that allows expressing rich temporal specifications and uses a semantic parser to provide a natural language interface. Flipper provides immediate visual feedback by executing an automatically constructed plan of the task in a graphical user interface. This allows the user to resolve potentially ambiguous interpretations. Flipper extends itself via naturalization: its users can add definitions for utterances, from which Flipper induces new rules and adds them to the core language, gradually growing a more and more natural task specification language. Flipper improves the naturalization by generalizing the definition provided by users. Unlike other task-specification systems, Flipper enables natural language interactions while maintaining the expressive power and formal precision of a programming language. We show through an initial user study that natural language interactions and generalization can considerably ease the description of tasks. Moreover, over time, users employ more and more concepts outside of the initial core language. Such extensions are available to the Flipper community, and users can use concepts that others have defined.
Prospection, the act of predicting the consequences of many possible futures, is intrinsic to human planning and action, and may even be at the root of consciousness. Surprisingly, this idea has been explored comparatively little in robotics. In this work, we propose a neural network architecture and associated planning algorithm that (1) learns a representation of the world useful for generating prospective futures after the application of high-level actions, (2) uses this generative model to simulate the result of sequences of high-level actions in a variety of environments, and (3) uses this same representation to evaluate these actions and perform tree search to find a sequence of high-level actions in a new environment. Models are trained via imitation learning on a variety of domains, including navigation, pick-and-place, and a surgical robotics task. Our approach allows us to visualize intermediate motion goals and learn to plan complex activity from visual information.
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 article, 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 for solving 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 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.
Understanding object states is as important as object recognition for robotic task planning and manipulation. To our knowledge, this paper explicitly introduces and addresses the state identification problem in cooking related images for the first time. In this paper, objects and ingredients in cooking videos are explored and the most frequent objects are analyzed. Eleven states from the most frequent cooking objects are examined and a dataset of images containing those objects and their states is created. As a solution to the state identification problem, a Resnet based deep model is proposed. The model is initialized with Imagenet weights and trained on the dataset of eleven classes. The trained state identification model is evaluated on a subset of the Imagenet dataset and state labels are provided using a combination of the model with manual checking. Moreover, an individual model is fine-tuned for each object in the dataset using the weights from the initially trained model and object-specific images, where significant improvement is demonstrated.
As autonomous service robots become more affordable and thus available also for the general public, there is a growing need for user friendly interfaces to control the robotic system. Currently available control modalities typically expect users to be able to express their desire through either touch, speech or gesture commands. While this requirement is fulfilled for the majority of users, paralyzed users may not be able to use such systems. In this paper, we present a novel framework, that allows these users to interact with a robotic service assistant in a closed-loop fashion, using only thoughts. The brain-computer interface (BCI) system is composed of several interacting components, i.e., non-invasive neuronal signal recording and decoding, high-level task planning, motion and manipulation planning as well as environment perception. In various experiments, we demonstrate its applicability and robustness in real world scenarios, considering fetch-and-carry tasks and tasks involving human-robot interaction. As our results demonstrate, our system is capable of adapting to frequent changes in the environment and reliably completing given tasks within a reasonable amount of time. Combined with high-level planning and autonomous robotic systems, interesting new perspectives open up for non-invasive BCI-based human-robot interactions.