LLMs have been widely used in planning, either as planners to generate action sequences end-to-end, or as formalizers to represent the planning domain and problem in a formal language that can derive plans deterministically.However, both lines of work rely on standard benchmarks that include only generic and simplistic environmental specifications, leading to potential overestimation of the planning ability of LLMs and safety concerns in downstream tasks.We bridge this gap by augmenting widely used planning benchmarks with manually annotated, fine-grained, and rich natural language constraints spanning four formally defined categories.Over 4 state-of-the-art reasoning LLMs, 4 formal languages, and 4 datasets, we show that the introduction of one-sentence constraints consistently halves performance, indicating current LLMs' lack of robustness and an avenue for future research.

To assist humans in open-world environments, robots must accurately interpret ambiguous instructions to locate desired objects. Foundation model-based approaches excel at reference expression grounding and multimodal instruction understanding, but lack a principled mechanism to model uncertainty in long-horizon tasks. Conversely, Partially Observable Markov Decision Processes (POMDPs) provide a systematic framework for planning under uncertainty but are typically limited in modalities and environment assumptions. To achieve the best of both worlds, we introduce Language and Gesture-Guided Object Search in Partially Observable Environments (LEGS-POMDP), a modular POMDP system that integrates language, gesture, and visual observations for open-world object search. Unlike prior work, LEGS-POMDP explicitly models two sources of partial observability: uncertainty over the target object’s identity and its spatial location. Simulation results show that multimodal fusion significantly outperforms unimodal baselines, achieving an average success rate of 89%±7% across challenging environments and object categories. Finally, we demonstrate the full system on a quadruped mobile manipulator, where real-world experiments qualitatively validate robust multimodal perception and uncertainty reduction under ambiguous human instructions.

When instructing robots, users want to flexibly express constraints, refer to arbitrary landmarks, and verify robot behavior, while robots must disambiguate instructions into specifications and ground instruction referents in the real world. To address this problem, we propose Language Instruction grounding for Motion Planning (LIMP), an approach that enables robots to verifiably follow complex, open-ended instructions in real-world environments without prebuilt semantic maps. LIMP constructs a symbolic instruction representation that reveals the robot's alignment with an instructor's intended motives and affords the synthesis of correct-by-construction robot behaviors. We conduct a large-scale evaluation of LIMP on 150 instructions across five real-world environments, demonstrating its versatility and ease of deployment in diverse, unstructured domains. LIMP performs comparably to state-of-the-art baselines on standard open-vocabulary tasks and additionally achieves a 79% success rate on complex spatiotemporal instructions, significantly outperforming baselines that only reach 38%.11See supplementary materials and demo videos at robotlimp.github.io

Learning to execute long-horizon mobile manipulation tasks is crucial for advancing robotics in household and workplace settings. However, current approaches are typically data-inefficient, underscoring the need for improved models that require realistically sized benchmarks to evaluate their efficiency. To address this, we introduce the LAMBDA (λ) benchmark1––Long-horizon Actions for Mobile-manipulation Benchmarking of Directed Activities––which evaluates the data efficiency of models on language-conditioned, long-horizon, multi-room, multi-floor, pick-and-place tasks using a dataset of manageable size, more feasible for collection. Our benchmark includes 571 human-collected demonstrations that provide realism and diversity in simulated and real-world settings. Unlike planner-generated data, these trajectories offer natural variability and replay-verifiability, ensuring robust learning and evaluation. We leverage λ to benchmark current end-to-end learning methods and a modular neuro-symbolic approach that combines foundation models with task and motion planning. We find that learning methods, even when pretrained, yield lower success rates, while a neuro-symbolic method performs significantly better and requires less data.

Deploying robots in real-world environments, such as households and manufacturing lines, requires generalization across novel task specifications without violating safety constraints. Linear temporal logic (LTL) is a widely used task specification language with a compositional grammar that naturally induces commonalities among tasks while preserving safety guarantees. However, most prior work on reinforcement learning with LTL specifications treats every new task independently, thus requiring large amounts of training data to generalize. We propose LTL-Transfer, a zero-shot transfer algorithm that composes task-agnostic skills learned during training to safely satisfy a wide variety of novel LTL task specifications. Experiments in Minecraft-inspired domains show that after training on only 50 tasks, LTL-Transfer can solve over 90% of 100 challenging unseen tasks and 100% of 300 commonly used novel tasks without violating any safety constraints. We deployed LTL-Transfer at the task-planning level of a quadruped mobile manipulator to demonstrate its zero-shot transfer ability for fetch-and-deliver and navigation tasks.

Extracting knowledge and reasoning from large language models (LLMs) offers a path to designing intelligent robots. Common approaches that leverage LLMs for planning are unable to recover when actions fail and resort to retrying failed actions without resolving the underlying cause. We propose a novel approach (CAPE) that generates corrective actions to resolve precondition errors during planning. CAPE improves the quality of generated plans through few-shot reasoning on action preconditions. Our approach enables embodied agents to execute more tasks than baseline methods while maintaining semantic correctness and minimizing re-prompting. In VirtualHome, CAPE improves a human-annotated plan correctness metric from 28.89% to 49.63% over SayCan, whilst achieving competitive executability. Our improvements transfer to a Boston Dynamics Spot robot initialized with a set of skills (specified in language) and associated preconditions, where CAPE improves correctness by 76.49% with higher executability compared to SayCan. Our approach enables embodied agents to follow natural language commands and robustly recover from failures.

Recent advancements in large language models (LLMs) have enabled a new research domain, LLM agents, for solving robotics and planning tasks by leveraging the world knowledge and general reasoning abilities of LLMs obtained during pretraining. However, while considerable effort has been made to teach the robot the "dos", the "don’ts" received relatively less attention. We argue that, for any practical usage, it is as crucial to teach the robot the "don’ts": conveying explicit instructions about prohibited actions, assessing the robot’s comprehension of these restrictions, and, most importantly, ensuring compliance. Moreover, verifiable safe operation is essential for deployments that satisfy worldwide standards such as ISO 61508, which defines standards for safely deploying robots in industrial factory environments worldwide. Aiming at deploying the LLM agents in a collaborative environment, we propose a queryable safety constraint module based on linear temporal logic (LTL) that simultaneously enables natural language (NL) to temporal constraints encoding, safety violation reasoning and explaining, and unsafe action pruning. To demonstrate the effectiveness of our system, we conducted experiments in VirtualHome environment and on a real robot. The experimental results show that our system strictly adheres to the safety constraints and scales well with complex safety constraints, highlighting its potential for practical utility.

Grounding spatiotemporal navigation commands to structured task specifications enables autonomous robots to understand a broad range of natural language and solve long-horizon tasks with safety guarantees. Prior works mostly focus on grounding spatial or temporally extended language for robots. We propose Lang2LTL-2, a modular system that leverages pretrained large language and vision-language models and multimodal semantic information to ground spatiotemporal navigation commands in novel city-scaled environments without retraining. Lang2LTL-2 achieves 93.53% language grounding accuracy on a dataset of 21,780 semantically diverse natural language commands in unseen environments. We run an ablation study to validate the need for different modalities. We also show that a physical robot equipped with the same system without modification can execute 50 semantically diverse natural language commands in both indoor and outdoor environments.

We introduce RLang, a domain-specific language (DSL) for communicating domain knowledge to an RL agent. Unlike existing RL DSLs that ground to $\textit{single}$ elements of a decision-making formalism (e.g., the reward function or policy), RLang can specify information about every element of a Markov decision process. We define precise syntax and grounding semantics for RLang, and provide a parser that grounds RLang programs to an algorithm-agnostic $\textit{partial}$ world model and policy that can be exploited by an RL agent. We provide a series of example RLang programs demonstrating how different RL methods can exploit the resulting knowledge, encompassing model-free and model-based tabular algorithms, policy gradient and value-based methods, hierarchical approaches, and deep methods.

Searching for objects is a fundamental skill for robots. As such, we expect object search to eventually become an off-the-shelf capability for robots, similar to e.g., object detection and SLAM. In contrast, however, no system for 3D object search exists that generalizes across real robots and environments. In this paper, building upon a recent theoretical framework that exploited the octree structure for representing belief in 3D, we present GenMOS (Generalized Multi-Object Search), the first general-purpose system for multi-object search (MOS) in a 3D region that is robot-independent and environment-agnostic. GenMOS takes as input point cloud observations of the local region, object detection results, and localization of the robot's view pose, and outputs a 6D viewpoint to move to through online planning. In particular, GenMOS uses point cloud observations in three ways: (1) to simulate occlusion; (2) to inform occupancy and initialize octree belief; and (3) to sample a belief-dependent graph of view positions that avoid obstacles. We evaluate our system both in simulation and on two real robot platforms. Our system enables, for example, a Boston Dynamics Spot robot to find a toy cat hidden underneath a couch in under one minute. We further integrate 3D local search with 2D global search to handle larger areas, demonstrating the resulting system in a 25m2lobby area.

Conversational assistive robots can aid people, especially those with cognitive impairments, to accomplish various tasks such as cooking meals, performing exercises, or operating machines. However, to interact with people effectively, robots must recognize human plans and goals from noisy observations of human actions, even when the user acts sub-optimally. Previous works on Plan and Goal Recognition (PGR) as planning have used hierarchical task networks (HTN) to model the actor/human. However, these techniques are insufficient as they do not have user engagement via natural modes of interaction such as language. Moreover, they have no mechanisms to let users, especially those with cognitive impairments, know of a deviation from their original plan or about any sub-optimal actions taken towards their goal. We propose a novel framework for plan and goal recognition in partially observable domains—Dialogue for Goal Recognition (D4GR) enabling a robot to rectify its belief in human progress by asking clarification questions about noisy sensor data and sub-optimal human actions. We evaluate the performance of D4GR over two simulated domains—kitchen and blocks domain. With language feedback and the world state information in a hierarchical task model, we show that D4GR framework for the highest sensor noise performs 1% better than HTN in goal accuracy in both domains. For plan accuracy, D4GR outperforms by 4% in the kitchen domain and 2% in the blocks domain in comparison to HTN. The ALWAYS-ASK oracle outperforms our policy by 3% in goal recognition and 7% in plan recognition. D4GR does so by asking 68% fewer questions than an oracle baseline. We also demonstrate a real-world robot scenario in the kitchen domain, validating the improved plan and goal recognition of D4GR in a realistic setting.

It is imperative that robots can understand natural language commands issued by humans. Such commands typically contain verbs that signify what action should be performed on a given object and that are applicable to many objects. We propose a method for generalizing manipulation skills to novel objects using verbs. Our method learns a probabilistic classifier that determines whether a given object trajectory can be described by a specific verb. We show that this classifier accurately generalizes to novel object categories with an average accuracy of 76.69% across 13 object categories and 14 verbs. We then perform policy search over the object kinematics to find an object trajectory that maximizes classifier prediction for a given verb. Our method allows a robot to generate a trajectory for a novel object based on a verb, which can then be used as input to a motion planner. We show that our model can generate trajectories that are usable for executing five verb commands applied to novel instances of two different object categories on a real robot.

Object search is a challenging task because when given complex language descriptions (e.g., “find the white cup on the table”), the robot must move its camera through the environment and recognize the described object. Previous works map language descriptions to a set of fixed object detectors with predetermined noise models, but these approaches are challenging to scale because new detectors need to be made for each object. In this work, we bridge the gap in realistic object search by posing the search problem as a partially observable Markov decision process (POMDP) where the object detector and visual sensor noise in the observation model is determined by a single Deep Neural Network conditioned on complex language descriptions. We incorporate the neural network's outputs into our language-conditioned observation model (LCOM) to represent dynamically changing sensor noise. With an LCOM, any language description of an object can be used to generate an appropriate object detector and noise model, and training an LCOM only requires readily available supervised image-caption datasets. We empirically evaluate our method by comparing against a state-of-the-art object search algorithm in simulation, and demonstrate that planning with our observation model yields a significantly higher average task completion rate (from 0.46 to 0.66) and more efficient and quicker object search than with a fixed-noise model. We demonstrate our method on a Boston Dynamics Spot robot, enabling it to handle complex natural language object descriptions and efficiently find objects in a room-scale environment.

Robots that process navigation instructions in large outdoor environments will need to operate at different levels of abstraction. For example, a land-surveying aerial robot receiving the instruction “go to Boston and go through the state forest on the way” must reason about a long-range goal like “go to Boston” while also processing a finer-grained constraint like “go through the state forest.” Existing approaches struggle to plan such commands because of the immense number of locations and constraints that can be expressed in language. We introduce a hierarchical representation of outdoor environments and a planning approach that dynamically compacts the robot's state space to enable tractable planning in city and state-scale environments. Our approach leverages natural abstractions in real-world map data, coupled with abstractions generated from users' instructions, to generate filtered environment views that accelerate planning while supporting a robot's ability to obey complex temporal goals and constraints at different levels of abstraction. We evaluate our approach on seven templates of LTLJ formulas and in an 80 kilometer-radius environment containing over 250,000 locations downloaded from OpenStreetMap. The results show our approach enables planning in seconds or minutes in a large outdoor environment while still satisfying the task specification.

Recent work on using natural language to specify commands to robots has grounded that language to LTL. However, mapping natural language task specifications to LTL task specifications using language models require probability distributions over finite vocabulary. Existing state-of-the-art methods have extended this finite vocabulary to include unseen terms from the input sequence to improve output generalization. However, novel out-of-vocabulary atomic propositions cannot be generated using these methods. To overcome this, we introduce an intermediate contextual query representation which can be learned from single positive task specification examples, associating a contextual query with an LTL template. We demonstrate that this intermediate representation allows for generalization over unseen object references, assuming accurate groundings are available. We compare our method of mapping natural language task specifications to intermediate contextual queries against state-of-the-art CopyNet models capable of translating natural language to LTL, by evaluating whether correct LTL for manipulation and navigation task specifications can be output, and show that our method outperforms the CopyNet model on unseen object references. We demonstrate that the grounded LTL our method outputs can be used for planning in a simulated OO-MDP environment. Finally, we discuss some common failure modes encountered when translating natural language task specifications to grounded LTL.

In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-detect objects. In such settings, correlational information can be valuable for planning efficiently. Previous approaches that consider correlational information typically resort to ad-hoc, greedy search strategies. We introduce the Correlational Object Search POMDP (COS-POMDP), which models correlations while preserving optimal solutions with a reduced state space. We propose a hierarchical planning algorithm to scale up COS-POMDPs for practical domains. Our evaluation, conducted with the AI2-THOR household simulator and the YOLOv5 object detector, shows that our method finds objects more successfully and efficiently compared to baselines, particularly for hard-to-detect objects such as srub brush and remote control.

With robotics rapidly advancing, more effective human–robot interaction is increasingly needed to realize the full potential of robots for society. While spoken language must be part of the solution, our ability to provide spoken language interaction capabilities is still very limited. In this article, based on the report of an interdisciplinary workshop convened by the National Science Foundation, we identify key scientific and engineering advances needed to enable effective spoken language interaction with robotics. We make 25 recommendations, involving eight general themes: putting human needs first, better modeling the social and interactive aspects of language, improving robustness, creating new methods for rapid adaptation, better integrating speech and language with other communication modalities, giving speech and language components access to rich representations of the robot’s current knowledge and state, making all components operate in real time, and improving research infrastructure and resources. Research and development that prioritizes these topics will, we believe, provide a solid foundation for the creation of speech-capable robots that are easy and effective for humans to work with.

Robots must reason about pushing and grasping in order to engage in flexible manipulation in cluttered environments. Earlier works on learning pushing and grasping only consider each operation in isolation or are limited to top-down grasping and bin-picking. We train a robot to learn joint planar pushing and 6-degree-of-freedom (6-DoF) grasping policies by self-supervision. Two separate deep neural networks are trained to map from 3D visual observations to actions with a Q-learning framework. With collaborative pushes and expanded grasping action space, our system can deal with cluttered scenes with a wide variety of objects (e.g. grasping a plate from the side after pushing away surrounding obstacles). We compare our system to the state-of-the-art baseline model VPG [1] in simulation and outperform it with 10% higher action efficiency and 20% higher grasp success rate. We then demonstrate our system on a KUKA LBR iiwa arm with a Robotiq 3-finger gripper.

Learning a robot motor skill from scratch is impractically slow; so much so that in practice, learning must typically be bootstrapped using human demonstration. However, relying on human demonstration necessarily degrades the autonomy of robots that must learn a wide variety of skills over their operational lifetimes. We propose using kinematic motion planning as a completely autonomous, sample efficient way to bootstrap motor skill learning for object manipulation. We demonstrate the use of motion planners to bootstrap motor skills in two complex object manipulation scenarios with different policy representations: opening a drawer with a dynamic movement primitive representation, and closing a microwave door with a deep neural network policy. We also show how our method can bootstrap a motor skill for the challenging dynamic task of learning to hit a ball off a tee, where a kinematic plan based on treating the scene as static is insufficient to solve the task, but sufficient to bootstrap a more dynamic policy. In all three cases, our method is competitive with human-demonstrated initialization, and significantly out-performs starting with a random policy. This approach enables robots to to efficiently and autonomously learn motor policies for dynamic tasks without human demonstration.

We propose an approach to multi-modal grasp detection that jointly predicts the probabilities that several types of grasps succeed at a given grasp pose. Given a partial point cloud of a scene, the algorithm proposes a set of feasible grasp candidates, then estimates the probabilities that a grasp of each type would succeed at each candidate pose. Predicting grasp success probabilities directly from point clouds makes our approach agnostic to the number and placement of depth sensors at execution time. We evaluate our system both in simulation and on a real robot with a Robotiq 3-Finger Adaptive Gripper and compare our network against several baselines that perform fewer types of grasps. Our experiments show that a system that explicitly models grasp type achieves an object retrieval rate 8.5% higher in a complex cluttered environment than our highest-performing baseline.

Robots operating in households must find objects on shelves, under tables, and in cupboards. In such environments, it is crucial to search efficiently at 3D scale while coping with limited field of view and the complexity of searching for multiple objects. Principled approaches to object search frequently use Partially Observable Markov Decision Process (POMDP) as the underlying framework for computing search strategies, but constrain the search space in 2D. In this paper, we present a POMDP formulation for multi-object search in a 3D region with a frustum-shaped field-of-view. To efficiently solve this POMDP, we propose a multi-resolution planning algorithm based on online Monte-Carlo tree search. In this approach, we design a novel octree-based belief representation to capture uncertainty of the target objects at different resolution levels, then derive abstract POMDPs at lower resolutions with dramatically smaller state and observation spaces. Evaluation in a simulated 3D domain shows that our approach finds objects more efficiently and successfully compared to a set of baselines without resolution hierarchy in larger instances under the same computational requirement. We demonstrate our approach on a mobile robot to find objects placed at different heights in two 10m2×2m regions by moving its base and actuating its torso.

Humans use spatial language to naturally describe object locations and their relations. Interpreting spatial language not only adds a perceptual modality for robots, but also reduces the barrier of interfacing with humans. Previous work primarily considers spatial language as goal specification for instruction following tasks in fully observable domains, often paired with reference paths for reward-based learning. However, spatial language is inherently subjective and potentially ambiguous or misleading. Hence, in this paper, we consider spatial language as a form of stochastic observation. We propose SLOOP (Spatial Language Object-Oriented POMDP), a new framework for partially observable decision making with a probabilistic observation model for spatial language. We apply SLOOP to object search in city-scale environments. To interpret ambiguous, context-dependent prepositions (e.g. front), we design a simple convolutional neural network that predicts the language provider’s latent frame of reference (FoR) given the environment context. Search strategies are computed via an online POMDP planner based on Monte Carlo Tree Search. Evaluation based on crowdsourced language data, collected over areas of five cities in OpenStreetMap, shows that our approach achieves faster search and higher success rate compared to baselines, with a wider margin as the spatial language becomes more complex. Finally, we demonstrate the proposed method in AirSim, a realistic simulator where a drone is tasked to find cars in a neighborhood environment.

We propose an abstraction method for open-world environments expressed as Factored Markov Decision Processes (FMDPs) with very large state and action spaces. Our method prunes state and action variables that are irrelevant to the optimal value function on the state subspace the agent would visit when following any optimal policy from the initial state. This method thus enables tractable fast planning within large open-world FMDPs.

Robots operating in outdoor, urban environments need the ability to follow complex natural language commands which refer to never-before-seen landmarks. Existing approaches to this problem are limited because they require training a language model for the landmarks of a particular environment before a robot can understand commands referring to those landmarks. To generalize to new environments outside of the training set, we present a framework that parses references to landmarks, then assesses semantic similarities between the referring expression and landmarks in a predefined semantic map of the world, and ultimately translates natural language commands to motion plans for a drone. This framework allows the robot to ground natural language phrases to landmarks in a map when both the referring expressions to landmarks and the landmarks themselves have not been seen during training. We test our framework with a 14-person user evaluation demonstrating an end-to-end accuracy of 76.19% in an unseen environment. Subjective measures show that users find our system to have high performance and low workload. These results demonstrate our approach enables untrained users to control a robot in large unseen outdoor environments with unconstrained natural language.

We propose Action-Oriented Semantic Maps (AOSMs), a representation that enables a robot to acquire object manipulation behaviors and semantic information about the environment from a human teacher with a Mixed Reality Head-Mounted Display (MR-HMD). AOSMs are a representation that captures both: a) high-level object manipulation actions in an object class's local frame, and b) semantic representations of objects in the robot's global map that are grounded for navigation. Humans can use a MR-HMD to teach the agent the information necessary for planning object manipulation and navigation actions by interacting with virtual 3D meshes overlaid on the physical workspace. We demonstrate that our system enables users to quickly and accurately teach a robot the knowledge required to autonomously plan and execute three household tasks: picking up a bottle and throwing it in the trash, closing a sink faucet, and flipping a light switch off.

We present a decision-theoretic model and robot system that interprets multimodal human communication to disambiguate item references by asking questions via a mixed reality (MR) interface. Existing approaches have either chosen to use physical behaviors, like pointing and eye gaze, or virtual behaviors, like mixed reality. However, there is a gap of research on how MR compares to physical actions for reducing robot uncertainty. We test the hypothesis that virtual deictic gestures are better for human-robot interaction (HRI) than physical behaviors. To test this hypothesis, we propose the Physio-Virtual Deixis Partially Observable Markov Decision Process (PVD-POMDP), which interprets multimodal observations (speech, eye gaze, and pointing gestures) from the human and decides when and how to ask questions (either via physical or virtual deictic gestures) in order to recover from failure states and cope with sensor noise. We conducted a between-subjects user study with 80 participants distributed across three conditions of robot communication: no feedback control, physical feedback, and MR feedback. We tested performance of each condition with objective measures (accuracy, time), as well as evaluated user experience with subjective measures (usability, trust, workload). We found the MR feedback condition was 10% more accurate than the physical condition and a speedup of 160%. We also found that the feedback conditions significantly outperformed the no feedback condition in all subjective metrics.

Security is particularly important in robotics, as robots can directly perceive and affect the physical world. We describe the results of a scan of the entire IPv4 address space of the Internet for instances of the Robot Operating System (ROS), a widely used robotics software platform. We identified a number of hosts supporting ROS that are exposed to the public Internet, thereby allowing anyone to access robotic sensors and actuators. As a proof of concept, and with the consent of the relevant researchers, we were able to read image sensor information from and actuate a physical robot present in a research lab in an American university. This paper gives an overview of our findings, including our methodology, the geographic distribution of publicly-accessible platforms, the sorts of sensor and actuator data that is available, and the different kinds of robots and sensors that our scan uncovered. Additionally, we offer recommendations on best practices to mitigate these security issues in the future.

Mixed Reality (MR) is a promising interface for robot programming because it can project an immersive 3D visualization of a robot's intended movement onto the real world. MR can also support hand gestures, which provide an intuitive way for users to construct and modify robot motions. We present a Mixed Reality Head-Mounted Display (MRHMD) interface that enables end-users to easily create and edit robot motions using waypoints. We describe a user study where 20 participants were asked to program a robot arm using 2D and MR interfaces to perform two pick-and-place tasks. In the primitive task, participants created typical pickand-place programs. In the adapted task, participants adapted their primitive programs to address a more complex pickand-place scenario, which included obstacles and conditional reasoning. Compared to the 2D interface, a higher number of users were able to complete both tasks in significantly less time, and reported experiencing lower cognitive workload, higher usability, and higher naturalness with the MR-HMD interface.

With increasing autonomy, robots like drones are increasingly accessible to untrained users. Most users control drones using a low-level interface, such as a radio-controlled (RC) controller. For a wider adoption of these technologies by the public, a much higher-level interface, such as natural language or mixed reality (MR), allows the automation of the control of the agent in a goal-oriented setting. We present an interface that uses natural language grounding within an MR environment to solve high-level task and navigational instructions given to an autonomous drone. To the best of our knowledge, this is the first work to perform fully autonomous language grounding in an MR setting for a robot. Given a map, our interface first grounds natural language commands to reward specifications within a Markov Decision Process (MDP) framework. Then, it passes the reward specification to an MDP solver. Finally, the drone performs the desired operations in the real world while planning and localizing itself. Our approach uses MR to provide a set of known virtual landmarks, enabling the drone to understand commands referring to objects without being equipped with object detectors for multiple novel objects or a predefined environment model. We conducted an exploratory user study to assess users' experience of our MR interface with and without natural language, as compared to a web interface. We found that users were able to command the drone more quickly via both MR interfaces as compared to the web interface, with roughly equal system usability scores across all three interfaces.

In this paper, we introduce an approach which enables manipulator robots to write handwritten characters or line drawings. Given an image of just-drawn handwritten characters, the robot infers a plan to replicate the image with a writing utensil, and then reproduces the image. Our approach draws each target stroke in one continuous drawing motion and does not rely on handcrafted rules or on predefined paths of characters. Instead, it learns to write from a dataset of demonstrations. We evaluate our approach in both simulation and on two real robots. Our model can draw handwritten characters in a variety of languages which are disjoint from the training set, such as Greek, Tamil, or Hindi, and also reproduce any stroke-based drawing from an image of the drawing.

A core capability of robots is to reason about multiple objects under uncertainty. Partially Observable Markov Decision Processes (POMDPs) provide a means of reasoning under uncertainty for sequential decision making, but are computationally intractable in large domains. In this paper, we propose Object-Oriented POMDPs (OO-POMDPs), which represent the state and observation spaces in terms of classes and objects. The structure afforded by OO-POMDPs support a factorization of the agent's belief into independent object distributions, which enables the size of the belief to scale linearly versus exponentially in the number of objects. We formulate a novel Multi-Object Search (MOS) task as an OO-POMDP for mobile robotics domains in which the agent must find the locations of multiple objects. Our solution exploits the structure of OO-POMDPs by featuring human language to selectively update the belief at task onset. Using this structure, we develop a new algorithm for efficiently solving OO-POMDPs: Object-Oriented Partially Observable Monte-Carlo Planning (OOPOMCP). We show that OO-POMCP with grounded language commands is sufficient for solving challenging MOS tasks both in simulation and on a physical mobile robot.

We develop a system to disambiguate object instances within the same class based on simple physical descriptions. The system takes as input a natural language phrase and a depth image containing a segmented object and predicts how similar the observed object is to the object described by the phrase. Our system is designed to learn from only a small amount of human-labeled language data and generalize to viewpoints not represented in the language-annotated depth image training set. By decoupling 3D shape representation from language representation, this method is able to ground language to novel objects using a small amount of language-annotated depth-data and a larger corpus of unlabeled 3D object meshes, even when these objects are partially observed from unusual viewpoints. Our system is able to disambiguate between novel objects, observed via depth images, based on natural language descriptions. Our method also enables viewpoint transfer; trained on human-annotated data on a small set of depth images captured from frontal viewpoints, our system successfully predicted object attributes from rear views despite having no such depth images in its training set. Finally, we demonstrate our approach on a Baxter robot, enabling it to pick specific objects based on human-provided natural language descriptions.

PiDrone is a quadrotor platform created to accompany an introductory robotics course. Students build an autonomous flying robot from scratch and learn to program it through assignments and projects. Existing educational robots do not have significant autonomous capabilities, such as high-level planning and mapping. We present a hardware and software framework for an autonomous aerial robot, in which all software for autonomy can run onboard the drone, implemented in Python. We present an Unscented Kalman Filter (UKF) for accurate state estimation. Next, we present an implementation of Monte Carlo (MC) Localization and FastSLAM for Simultaneous Localization and Mapping (SLAM). The performance of UKF, localization, and SLAM is tested and compared to ground truth, provided by a motion-capture system. Our evaluation demonstrates that our autonomous educational framework runs quickly and accurately on a Raspberry Pi in Python, making it ideal for use in educational settings.

In order to intuitively and efficiently collaborate with humans, robots must learn to complete tasks specified using natural language. We represent natural language instructions as goal-state reward functions specified using lambda calculus. Using reward functions as language representations allows robots to plan efficiently in stochastic environments. To map sentences to such reward functions, we learn a weighted linear Combinatory Categorial Grammar (CCG) semantic parser. The parser, including both parameters and the CCG lexicon, is learned from a validation procedure that does not require execution of a planner, annotating reward functions, or labeling parse trees, unlike prior approaches. To learn a CCG lexicon and parse weights, we use coarse lexical generation and validation-driven perceptron weight updates using the approach of Artzi and Zettlemoyer [4]. We present results on the Cleanup World domain [18] to demonstrate the potential of our approach. We report an F1 score of 0.82 on a collected corpus of 23 tasks containing combinations of nested referential expressions, comparators and object properties with 2037 corresponding sentences. Our goal-condition learning approach enables an improvement of orders of magnitude in computation time over a baseline that performs planning during learning, while achieving comparable results. Further, we conduct an experiment with just 6 labeled demonstrations to show the ease of teaching a robot behaviors using our method. We show that parsing models learned from small data sets can generalize to commands not seen during training.

Virtual reality (VR)systems let users intuitively interact with 3D environments and have been used extensively for robotic teleoperation tasks. While more immersive than their 2D counterparts, early VR systems were expensive and required specialized hardware. Fortunately, there has been a recent proliferation of consumer-grade VR systems at affordable price points. These systems are inexpensive, relatively portable, and can be integrated into existing robotic frameworks. Our group has designed a VR teleoperation package for the Robot Operating System (ROS), ROS Reality, that can be easily integrated into such frameworks. ROS Reality is an open-source, over-the-Internet teleoperation interface between any ROS-enabled robot and any Unity-compatible VR headset. We completed a pilot study to test the efficacy of our system, with expert human users controlling a Baxter robot via ROS Reality to complete 24 dexterous manipulation tasks, compared to the same users controlling the robot via direct kinesthetic handling. This study provides insight into the feasibility of robotic teleoperation tasks in VR with current consumer-grade resources and exposes issues that need to be addressed in these VR systems. In addition, this paper presents a description of ROS Reality, its components, and architecture. We hope this system will be adopted by other research groups to allow for easy integration of VR teleoperated robots into future experiments.

Fetching items is an important problem for a social robot. It requires a robot to interpret a person's language and gesture and use these noisy observations to infer what item to deliver. If the robot could ask questions, it would help the robot be faster and more accurate in its task. Existing approaches either do not ask questions, or rely on fixed question-asking policies. To address this problem, we propose a model that makes assumptions about cooperation between agents to perform richer signal extraction from observations. This work defines a mathematical framework for an item-fetching domain that allows a robot to increase the speed and accuracy of its ability to interpret a person's requests by reasoning about its own uncertainty as well as processing implicit information (implicatures). We formalize the item-delivery domain as a Partially Observable Markov Decision Process (POMDP), and approximately solve this POMDP in real time. Our model improves speed and accuracy of fetching tasks by asking relevant clarifying questions only when necessary. To measure our model's improvements, we conducted a real world user study with 16 participants. Our method achieved greater accuracy and a faster interaction time compared to state-of-the-art baselines. Our model is 2.17 seconds faster (25% faster) than a state-of-the-art baseline, while being 2.1% more accurate.

Humans communicate about objects using language, gesture, and context, fusing information from multiple modalities over time. Robots need to interpret this communication in order to collaborate with humans on shared tasks. Processing communicative input incrementally has the potential to increase the speed and accuracy of a robot's reaction. It also enables the robot to incorporate the relative timing of words and gestures into the understanding process. To address this problem, we define a multimodal Bayes filter for interpreting a person's referential expressions to objects. Our approach outputs a distribution over the referent object at 14Hz, updating dynamically as it receives new observations of the person's spoken words and gestures. We collected a new dataset of people referring to one of four objects in a tabletop setting and demonstrate that our approach is able to infer the correct object with 90% accuracy. Additionally, we augment and improve our filter in a simulated home kitchen domain by learning contextual knowledge in an unsupervised manner from existing written text, increasing our maximum accuracy to 96%, even with an increase in the number of objects from four to seventy.

We describe a semantic mapping algorithm that learns human-centric environment models by interpreting natural language utterances. Underlying the approach is a coupled metric, topological, and semantic representation of the environment that enables the method to fuse information from natural language descriptions with low-level metric and appearance data. We extend earlier work with a novel formulation that incorporates spatial layout into a topological representation of the environment. We also describe a factor graph formulation of the semantic properties that encodes human-centric concepts such as type and colloquial name for each mapped region. The algorithm infers these properties by combining the user's natural language descriptions with image- and laser-based scene classification. We also propose a mechanism to more effectively ground natural language descriptions of distant regions using semantic cues from other modalities. We describe how the algorithm employs this learned semantic information to propose valid topological hypotheses, leading to more accurate topological and metric maps. We demonstrate that integrating language with other sensor data increases the accuracy of the achieved spatial-semantic representation of the environment.

Natural language interfaces for robot control aspire to find the best sequence of actions that reflect the behavior intended by the instruction. This is difficult because of the diversity of language, variety of environments, and heterogeneity of tasks. Previous work has demonstrated that probabilistic graphical models constructed from the parse structure of natural language can be used to identify motions that most closely resemble verb phrases. Such approaches however quickly succumb to computational bottlenecks imposed by construction and search the space of possible actions. Planning constraints, which define goal regions and separate the admissible and inadmissible states in an environment model, provide an interesting alternative to represent the meaning of verb phrases. In this paper we present a new model called the Distributed Correspondence Graph (DCG) to infer the most likely set of planning constraints from natural language instructions. A trajectory planner then uses these planning constraints to find a sequence of actions that resemble the instruction. Separating the problem of identifying the action encoded by the language into individual steps of planning constraint inference and motion planning enables us to avoid computational costs associated with generation and evaluation of many trajectories. We present experimental results from comparative experiments that demonstrate improvements in efficiency in natural language understanding without loss of accuracy.

Our goal is to improve the efficiency and effectiveness of natural language communication between humans and robots. Human language is frequently ambiguous, and a robot's limited sensing makes complete understanding of a statement even more difficult. To address these challenges, we describe an approach for enabling a robot to engage in clarifying dialog with a human partner, just as a human might do in a similar situation. Given an unconstrained command from a human operator, the robot asks one or more questions and receives natural language answers from the human. We apply an information-theoretic approach to choosing questions for the robot to ask. Specifically, we choose the type and subject of questions in order to maximize the reduction in Shannon entropy of the robot's mapping between language and entities in the world. Within the framework of the G3 graphical model, we derive a method to estimate this entropy reduction, choose the optimal question to ask, and merge the information gained from the human operator's answer. We demonstrate that this improves the accuracy of command understanding over prior work while asking fewer questions as compared to baseline question-selection strategies.

This paper describes a new model for understanding natural language commands given to autonomous systems that perform navigation and mobile manipulation in semi-structured environments. Previous approaches have used models with fixed structure to infer the likelihood of a sequence of actions given the environment and the command. In contrast, our framework, called Generalized Grounding Graphs, dynamically instantiates a probabilistic graphical model for a particular natural language command according to the command's hierarchical and compositional semantic structure. Our system performs inference in the model to successfully find and execute plans corresponding to natural language commands such as "Put the tire pallet on the truck." The model is trained using a corpus of commands collected using crowdsourcing. We pair each command with robot actions and use the corpus to learn the parameters of the model. We evaluate the robot's performance by inferring plans from natural language commands, executing each plan in a realistic robot simulator, and asking users to evaluate the system's performance. We demonstrate that our system can successfully follow many natural language commands from the corpus.

Speaking using unconstrained natural language is an intuitive and flexible way for humans to interact with robots. Understanding this kind of linguistic input is challenging because diverse words and phrases must be mapped into structures that the robot can understand, and elements in those structures must be grounded in an uncertain environment. We present a system that follows natural language directions by extracting a sequence of spatial description clauses from the linguistic input and then infers the most probable path through the environment given only information about the environmental geometry and detected visible objects. We use a probabilistic graphical model that factors into three key components. The first component grounds landmark phrases such as "the computers" in the perceptual frame of the robot by exploiting co-occurrence statistics from a database of tagged images such as Flickr. Second, a spatial reasoning component judges how well spatial relations such as "past the computers" describe a path. Finally, verb phrases such as "turn right" are modeled according to the amount of change in orientation in the path. Our system follows 60% of the directions in our corpus to within 15 meters of the true destination, significantly outperforming other approaches.

Natural language is a flexible and intuitive modality for conveying directions and commands to a robot but presents a number of computational challenges. Diverse words and phrases must be mapped into structures that the robot can understand, and elements in those structures must be grounded in an uncertain environment. In this paper we present a micro-air vehicle (MAV) capable of following natural language directions through a previously mapped and labeled environment. We extend our previous work in understanding 2D natural language directions to three dimensions, accommodating new verb modifiers such as go up and go down, and commands such as turn around and face the windows. We demonstrate the robot following directions created by a human for another human, and interactively executing commands in the context of surveillance and search and rescue in confined spaces. In an informal study, 71% of the paths computed from directions given by one user terminated within 10 m of the desired destination.

Spatial language video retrieval is an important real-world problem that forms a test bed for evaluating semantic structures for natural language descriptions of motion on naturalistic data. Video search by natural language query requires that linguistic input be converted into structures that operate on video in order to find clips that match a query. This paper describes a framework for grounding the meaning of spatial prepositions in video. We present a library of features that can be used to automatically classify a video clip based on whether it matches a natural language query. To evaluate these features, we collected a corpus of natural language descriptions about the motion of people in video clips. We characterize the language used in the corpus, and use it to train and test models for the meanings of the spatial prepositions "to," "across," "through," "out," "along," "towards," and "around." The classifiers can be used to build a spatial language video retrieval system that finds clips matching queries such as "across the kitchen."

The use of natural language should be added to a robot system without sacrificing responsiveness to the environment. In this paper, we present a robot that manipulates objects on a tabletop in response to verbal interaction. Reactivity is maintained by using concurrent interaction processes, such as visual trackers and collision detection processes. The interaction processes and their associated data are organized into object schemas, each representing a physical object in the environment, based on the target of each process. The object schemas then serve as discrete structures of coordination between reactivity, planning, and language use, permitting rapid integration of information from multiple sources.

An approach is introduced for physically grounded natural language interpretation by robots that reacts appropriately to unanticipated physical changes in the environment and dynamically assimilates new information pertinent to ongoing tasks. At the core of the approach is a model of object schemas that enables a robot to encode beliefs about physical objects in its environment using collections of coupled processes responsible for sensorimotor interaction. These interaction processes run concurrently in order to ensure responsiveness to the environment, while co-ordinating sensorimotor expectations, action planning and language use. The model has been implemented on a robot that manipulates objects on a tabletop in response to verbal input. The implementation responds to verbal requests such as ‘Group the green block and the red apple’, while adapting in real time to unexpected physical collisions and taking opportunistic advantage of any new information it may receive through perceptual and linguistic channels.

We have defined a lexicon of words in terms of spatial routines, and used that lexicon to build a speech controlled vehicle in a simulator. A spatial routine is a script composed from a set of primitive operations on occupancy grids, analogous to Ullman's visual routines. The vehicle understands the meaning of context-dependent natural language commands such as "Go across the room." When the system receives a command, it combines definitions from the lexicon according to the parse structure of the command, creating a script that selects a goal for the vehicle. Spatial routines may provide the basis for interpreting spatial language in a broad range of physically situated language understanding systems.

Passage retrieval is an important component common to many question answering systems. Because most evaluations of question answering systems focus on end-to-end performance, comparison of common components becomes di#cult. To address this shortcoming, we present a quantitative evaluation of various passage retrieval algorithms for question answering, implemented in a framework called Pauchok. We present three important findings: Boolean querying schemes perform well in the question answering task. The performance di#erences between various passage retrieval algorithms vary with the choice of document retriever, which suggests significant interactions between document retrieval and passage retrieval. The best algorithms in our evaluation employ density-based measures for scoring query terms. Our results reveal future directions for passage retrieval and question answering.