We present a self-supervised framework that learns population-level codes for arbitrary ensembles of neural recordings at scale. We address key challenges in scaling models with neural time-series data, namely, sparse and variable electrode distribution across subjects and datasets. The Population Transformer (PopT) stacks on top of pretrained temporal embeddings and enhances downstream decoding by enabling learned aggregation of multiple spatially-sparse data channels. The pretrained PopT lowers the amount of data required for downstream decoding experiments, while increasing accuracy, even on held-out subjects and tasks. Compared to end-to-end methods, this approach is computationally lightweight, while achieving similar or better decoding performance. We further show how our framework is generalizable to multiple time-series embeddings and neural data modalities. Beyond decoding, we interpret the pretrained and fine-tuned PopT models to show how they can be used to extract neuroscience insights from large amounts of data. We release our code as well as a pretrained PopT to enable off-the-shelf improvements in multi-channel intracranial data decoding and interpretability. Code is available at https://github.com/czlwang/PopulationTransformer.

We demonstrate that architectures which traditionally are considered to be ill-suited for a task can be trained using inductive biases from another architecture. We call a network untrainable when it overfits, underfits, or converges to poor results even when tuning their hyperparameters. For example, fully connected networks overfit on object recognition while deep convolutional networks without residual connections underfit. The traditional answer is to change the architecture to impose some inductive bias, although the nature of that bias is unknown. We introduce guidance, where a guide network steers a target network using a neural distance function. The target minimizes its task loss plus a layerwise representational similarity against the frozen guide. If the guide is trained, this transfers over the architectural prior and knowledge of the guide to the target. If the guide is untrained, this transfers over only part of the architectural prior of the guide. We show that guidance prevents FCN overfitting on ImageNet, narrows the vanilla RNN–Transformer gap, boosts plain CNNs toward ResNet accuracy, and aids Transformers on RNN-favored tasks. We further identify that guidance-driven initialization alone can mitigate FCN overfitting. Our method provides a mathematical tool to investigate priors and architectures, and in the long term, could automate architecture design.

We use (multi)modal deep neural networks (DNNs) to probe for sites of multimodal integration in the human brain by predicting stereoencephalography (SEEG) recordings taken while human subjects watched movies. We operationalize sites of multimodal integration as regions where a multimodal vision-language model predicts recordings better than unimodal language, unimodal vision, or linearly-integrated language-vision models. Our target DNN models span different architectures (e.g., convolutional networks and transformers) and multimodal training techniques (e.g., cross-attention and contrastive learning). As a key enabling step, we first demonstrate that trained vision and language models systematically outperform their randomly initialized counterparts in their ability to predict SEEG signals. We then compare unimodal and multimodal models against one another. Because our target DNN models often have different architectures, number of parameters, and training sets (possibly obscuring those differences attributable to integration), we carry out a controlled comparison of two models (SLIP and SimCLR), which keep all of these attributes the same aside from input modality. Using this approach, we identify a sizable number of neural sites (on average 141 out of 1090 total sites or 12.94%) and brain regions where multimodal integration seems to occur. Additionally, we find that among the variants of multimodal training techniques we assess, CLIP-style training is the best suited for downstream prediction of the neural activity in these sites.

When evaluating stimuli reconstruction results it is tempting to assume that higher fidelity text and image generation is due to an improved understanding of the brain or more powerful signal extraction from neural recordings. However, in practice, new reconstruction methods could improve performance for at least three other reasons: learning more about the distribution of stimuli, becoming better at reconstructing text or images in general, or exploiting weaknesses in current image and/or text evaluation metrics. Here we disentangle how much of the reconstruction is due to these other factors vs. productively using the neural recordings. We introduce BrainBits, a method that uses a bottleneck to quantify the amount of signal extracted from neural recordings that is actually necessary to reproduce a method's reconstruction fidelity. We find that it takes surprisingly little information from the brain to produce reconstructions with high fidelity. In these cases, it is clear that the priors of the methods' generative models are so powerful that the outputs they produce extrapolate far beyond the neural signal they decode. Given that reconstructing stimuli can be improved independently by either improving signal extraction from the brain or by building more powerful generative models, improving the latter may fool us into thinking we are improving the former. We propose that methods should report a method-specific random baseline, a reconstruction ceiling, and a curve of performance as a function of bottleneck size, with the ultimate goal of using more of the neural recordings.

We present the Brain Treebank, a large-scale dataset of electrophysiological neural responses, recorded from intracranial probes while 10 subjects watched one or more Hollywood movies. Subjects watched on average 2.6 Hollywood movies, for an average viewing time of 4.3 hours, and a total of 43 hours. The audio track for each movie was transcribed with manual corrections. Word onsets were manually annotated on spectrograms of the audio track for each movie. Each transcript was automatically parsed and manually corrected into the universal dependencies (UD) formalism, assigning a part of speech to every word and a dependency parse to every sentence. In total, subjects heard over 38,000 sentences (223,000 words), while they had on average 168 electrodes implanted. This is the largest dataset of intracranial recordings featuring grounded naturalistic language, one of the largest English UD treebanks in general, and one of only a few UD treebanks aligned to multimodal features. We hope that this dataset serves as a bridge between linguistic concepts, perception, and their neural representations. To that end, we present an analysis of which electrodes are sensitive to language features while also mapping out a rough time course of language processing across these electrodes. The Brain Treebank is available at https://BrainTreebank.dev/

Humans and animals engage in rich social interactions. It is often theorized that a relatively small number of basic social interactions give rise to the full range of behavior observed. But no computational theory explaining how social interactions combine together has been proposed before. We do so here. We take a model, the Social MDP, which is able to express a range of social interactions, and extend it to represent linear combinations of social interactions. Practically for robotics applications, such models are now able to not just express that an agent should help another agent, but to express goal-centric social interactions. Perhaps an agent is helping someone get dressed, but preventing them from falling, and is happy to exchange stories in the meantime. How an agent responds socially, should depend on what it thinks the other agent is doing at that point in time. To encode this notion, we take linear combinations of social interactions as defined in Social MDPs, and compute the weights on those combinations on the fly depending on the estimated goals of other agents. This new model, the Linear Social MDP, enables zero-shot reasoning about complex social interactions, provides a mathematical basis for the long-standing intuition that social interactions should compose, and leads to interesting new behaviors that we validate using human observers. Complex social interactions are part of the future of intelligent agents, and having principled mathematical models built on a foundation like MDPs will make it possible to bring social interactions to every robotic application.

Humans outperform object recognizers despite the fact that models perform well on current datasets, including those explicitly designed to challenge machines with debiased images or distribution shift. This problem persists, in part, because we have no guidance on the absolute difficulty of an image or dataset making it hard to objectively assess progress toward human-level performance, to cover the range of human abilities, and to increase the challenge posed by a dataset. We develop a dataset difficulty metric MVT, Minimum Viewing Time, that addresses these three problems. Subjects view an image that flashes on screen and then classify the object in the image. Images that require brief flashes to recognize are easy, those which require seconds of viewing are hard. We compute the ImageNet and ObjectNet image difficulty distribution, which we find significantly undersamples hard images. Nearly 90% of current benchmark performance is derived from images that are easy for humans. Rather than hoping that we will make harder datasets, we can for the first time objectively guide dataset difficulty during development. We can also subset recognition performance as a function of difficulty: model performance drops precipitously while human performance remains stable. Difficulty provides a new lens through which to view model performance, one which uncovers new scaling laws: vision-language models stand out as being the most robust and human-like while all other techniques scale poorly. We release tools to automatically compute MVT, along with image sets which are tagged by difficulty. Objective image difficulty has practical applications – one can measure how hard a test set is before deploying a real-world system – and scientific applications such as discovering the neural correlates of image difficulty and enabling new object recognition techniques that eliminate the benchmark-vs- real-world performance gap.

Adam Yaari, Jan DeWitt, Henry Hu, Bennett Stankovits, Sue Felshin, Yevgeni Berzak, Helena Aparicio, Boris Katz, Ignacio Cases, Andrei Barbu. Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing. 2022.

Language allows humans to build mental models that interpret what is happening around them resulting in more accurate long-term predictions. We present a novel trajectory prediction model that uses linguistic intermediate representations to forecast trajectories, and is trained using trajectory samples with partially-annotated captions. The model learns the meaning of each of the words without direct per-word supervision. At inference time, it generates a linguistic description of trajectories which captures maneuvers and interactions over an extended time interval. This generated description is used to refine predictions of the trajectories of multiple agents. We train and validate our model on the Argoverse dataset, and demonstrate improved accuracy results in trajectory prediction. In addition, our model is more interpretable: it presents part of its reasoning in plain language as captions, which can aid model development and can aid in building confidence in the model before deploying it.

Much of what we do as humans is engage socially with other agents, a skill that robots must also eventually possess. We demonstrate that a rich theory of social interactions originating from microsociology can be formalized by extending a nested MDP where agents reason about arbitrary functions of each other's rewards. This extended Social MDP allows us to encode the five basic interactions that underlie microsociology: cooperation, conflict, coercion, competition, and exchange. The result is a robotic agent capable of executing social interactions in new environments with no interaction-specific training; like humans it can engage socially in novel ways even without a single example of that social interaction. Moreover, the estimations of these Social MDPs align closely with the judge-ments of humans when considering which social interaction is taking place in an environment. This method both sheds light on the nature of social interactions, by providing concrete mathematical definitions, and brings rich social interactions into a mathematical framework that has proven to be natural for robotics.

The ability to perceive and reason about social interactions in the context of physical environments is core to human social intelligence and human-machine cooperation. However, no prior dataset or benchmark has systematically evaluated physically grounded perception of complex social interactions that go beyond short actions, such as high-fiving, or simple group activities, such as gathering. In this work, we create a dataset of physically-grounded abstract social events, PHASE, that resemble a wide range of real-life social interactions by including social concepts such as helping another agent. PHASE consists of 2D animations of pairs of agents moving in a continuous space generated procedurally using a physics engine and a hierarchical planner. Agents have a limited field of view, and can interact with multiple objects, in an environment that has multiple landmarks and obstacles. Using PHASE, we design a social recognition task and a social prediction task. PHASE is validated with human experiments demonstrating that humans perceive rich interactions in the social events, and that the simulated agents behave similarly to humans. As a baseline model, we introduce a Bayesian inverse planning approach, SIMPLE (SIMulation, Planning and Local Estimation), which outperforms state-of-the-art feed-forward neural networks. We hope that PHASE can serve as a difficult new challenge for developing new models that can recognize complex social interactions.

Visually-grounded spoken language datasets can enable models to learn cross-modal correspondences with very weak supervision.However, modern audio-visual datasets contain biases that undermine the real-world performance of models trained on that data.We introduce Spoken ObjectNet, which is designed to remove some of these biases and provide a way to better evaluate how effectively models will perform in real-world scenarios.This dataset expands upon ObjectNet, which is a biascontrolled image dataset that features similar image classes to those present in ImageNet.We detail our data collection pipeline, which features several methods to improve caption quality, including automated language model checks.Lastly, we show baseline results on image retrieval and audio retrieval tasks.These results show that models trained on other datasets and then evaluated on Spoken ObjectNet tend to perform poorly due to biases in other datasets that the models have learned.We also show evidence that the performance decrease is due to the dataset controls, and not the transfer setting.

We generalize the notion of measuring social biases in word embeddings to visually grounded word embeddings.Biases are present in grounded embeddings, and indeed seem to be equally or more significant than for ungrounded embeddings.This is despite the fact that vision and language can suffer from different biases, which one might hope could attenuate the biases in both.Multiple ways exist to generalize metrics measuring bias in word embeddings to this new setting.We introduce the space of generalizations (Grounded-WEAT and Grounded-SEAT) and demonstrate that three generalizations answer different yet important questions about how biases, language, and vision interact.These metrics are used on a new dataset, the first for grounded bias, created by augmenting standard linguistic bias benchmarks with 10,228 images from COCO, Conceptual Captions, and Google Images.Dataset construction is challenging because vision datasets are themselves very biased.The presence of these biases in systems will begin to have real-world consequences as they are deployed, making carefully measuring bias and then mitigating it critical to building a fair society.

How well do deep neural networks fare as models of mouse visual cortex? A majority of research to date suggests results far more mixed than those produced in the modeling of primate visual cortex. Here, we perform a large-scale benchmarking of dozens of deep neural network models in mouse visual cortex with both representational similarity analysis and neural regression. Using the Allen Brain Observatory's 2-photon calcium-imaging dataset of activity in over 6,000 reliable rodent visual cortical neurons recorded in response to natural scenes, we replicate previous findings and resolve previous discrepancies, ultimately demonstrating that modern neural networks can in fact be used to explain activity in the mouse visual cortex to a more reasonable degree than previously suggested. Using our benchmark as an atlas, we offer preliminary answers to overarching questions about levels of analysis (e.g. do models that better predict the representations of individual neurons also predict representational similarity across neural populations?); questions about the properties of models that best predict the visual system overall (e.g. is convolution or category-supervision necessary to better predict neural activity?); and questions about the mapping between biological and artificial representations (e.g. does the information processing hierarchy in deep nets match the anatomical hierarchy of mouse visual cortex?). Along the way, we catalogue a number of models (including vision transformers, MLP-Mixers, normalization free networks, Taskonomy encoders and self-supervised models) outside the traditional circuit of convolutional object recognition. Taken together, our results provide a reference point for future ventures in the deep neural network modeling of mouse visual cortex, hinting at novel combinations of mapping method, architecture, and task to more fully characterize the computational motifs of visual representation in a species so central to neuroscience, but with a perceptual physiology and ecology markedly different from the ones we study in primates.

We demonstrate how a sampling-based robotic planner can be augmented to learn to understand a sequence of natural language commands in a continuous configuration space to move and manipulate objects. Our approach combines a deep network structured according to the parse of a complex command that includes objects, verbs, spatial relations, and attributes, with a sampling-based planner, RRT. A recurrent hierarchical deep network controls how the planner explores the environment, determines when a planned path is likely to achieve a goal, and estimates the confidence of each move to trade off exploitation and exploration between the network and the planner. Planners are designed to have near-optimal behavior when information about the task is missing, while networks learn to exploit observations which are available from the environment, making the two naturally complementary. Combining the two enables generalization to new maps, new kinds of obstacles, and more complex sentences that do not occur in the training set. Little data is required to train the model despite it jointly acquiring a CNN that extracts features from the environment as it learns the meanings of words. The model provides a level of interpretability through the use of attention maps allowing users to see its reasoning steps despite being an end-to-end model. This end-to-end model allows robots to learn to follow natural language commands in challenging continuous environments.

We demonstrate a reinforcement learning agent which uses a compositional recurrent neural network that takes as input an LTL formula and determines satisfying actions. The input LTL formulas have never been seen before, yet the network performs zero-shot generalization to satisfy them. This is a novel form of multi-task learning for RL agents where agents learn from one diverse set of tasks and generalize to a new set of diverse tasks. The formulation of the network enables this capacity to generalize. We demonstrate this ability in two domains. In a symbolic domain, the agent finds a sequence of letters that is accepted. In a Minecraft-like environment, the agent finds a sequence of actions that conform to the formula. While prior work could learn to execute one formula reliably given examples of that formula, we demonstrate how to encode all formulas reliably. This could form the basis of new multitask agents that discover sub-tasks and execute them without any additional training, as well as the agents which follow more complex linguistic commands. The structures required for this generalization are specific to LTL formulas, which opens up an interesting theoretical question: what structures are required in neural networks for zero-shot generalization to different logics?

We collect a large real-world test set, ObjectNet, for object recognition with controls where object backgrounds, rotations, and imaging viewpoints are random. Most scientific experiments have controls, confounds which are removed from the data, to ensure that subjects cannot perform a task by exploiting trivial correlations in the data. Historically, large machine learning and computer vision datasets have lacked such controls. This has resulted in models that must be fine-tuned for new datasets and perform better on datasets than in real-world applications. When tested on ObjectNet, object detectors show a 40-45% drop in performance, with respect to their performance on other benchmarks, due to the controls for biases. Controls make ObjectNet robust to fine-tuning showing only small performance increases. We develop a highly automated platform that enables gathering datasets with controls by crowdsourcing image capturing and annotation. ObjectNet is the same size as the ImageNet test set (50,000 images), and by design does not come paired with a training set in order to encourage generalization. The dataset is both easier than ImageNet (objects are largely centered and unoccluded) and harder (due to the controls). Although we focus on object recognition here, data with controls can be gathered at scale using automated tools throughout machine learning to generate datasets that exercise models in new ways thus providing valuable feedback to researchers. This work opens up new avenues for research in generalizable, robust, and more human-like computer vision and in creating datasets where results are predictive of real-world performance.

We develop a semantic parser that is trained in a grounded setting using pairs of videos captioned with sentences. This setting is both data-efficient, requiring little annotation, and similar to the experience of children where they observe their environment and listen to speakers. The semantic parser recovers the meaning of English sentences despite not having access to any annotated sentences. It does so despite the ambiguity inherent in vision where a sentence may refer to any combination of objects, object properties, relations or actions taken by any agent in a video. For this task, we collected a new dataset for grounded language acquisition. Learning a grounded semantic parser — turning sentences into logical forms using captioned videos — can significantly expand the range of data that parsers can be trained on, lower the effort of training a semantic parser, and ultimately lead to a better understanding of child language acquisition.

We demonstrate how a sequence model and a sampling-based planner can influence each other to produce efficient plans and how such a model can automatically learn to take advantage of observations of the environment. Sampling-based planners such as RRT generally know nothing of their environments even if they have traversed similar spaces many times. A sequence model, such as an HMM or LSTM, guides the search for good paths. The resulting model, called DeRRT*, observes the state of the planner and the local environment to bias the next move and next planner state. The neural-network-based models avoid manual feature engineering by co-training a convolutional network which processes map features and observations from sensors. We incorporate this sequence model in a manner that combines its likelihood with the existing bias for searching large unexplored Voronoi regions. This leads to more efficient trajectories with fewer rejected samples even in difficult domains such as when escaping bug traps. This model can also be used for dimensionality reduction in multi-agent environments with dynamic obstacles. Instead of planning in a high-dimensional space that includes the configurations of the other agents, we plan in a low-dimensional subspace relying on the sequence model to bias samples using the observed behavior of the other agents. The techniques presented here are general, include both graphical models and deep learning approaches, and can be adapted to a range of planners.

A robot’s ability to understand or ground natural language instructions is fundamentally tied to its knowledge about the surrounding world. We present an approach to grounding natural language utterances in the context of factual information gathered through natural-language interactions and past visual observations. A probabilistic model estimates, from a natural language utterance, the objects, relations, and actions that the utterance refers to, the objectives for future robotic actions it implies, and generates a plan to execute those actions while updating a state representation to include newly acquired knowledge from the visual-linguistic context. Grounding a command necessitates a representation for past observations and interactions; however, maintaining the full context consisting of all possible observed objects, attributes, spatial relations, actions, etc., over time is intractable. Instead, our model, Temporal Grounding Graphs, maintains a learned state representation for a belief over factual groundings, those derived from natural-language interactions, and lazily infers new groundings from visual observations using the context implied by the utterance. This work significantly expands the range of language that a robot can understand by incorporating factual knowledge and observations of its workspace into its inference about the meaning and grounding of natural-language utterances.

We present a study on two key characteristics of human syntactic annotations: anchoring and agreement. Anchoring is a well known cognitive bias in human decision making, where judgments are drawn towards pre-existing values. We study the influence of anchoring on a standard approach to creation of syntactic resources where syntactic annotations are obtained via human editing of tagger and parser output. Our experiments demonstrate a clear anchoring effect and reveal unwanted consequences, including overestimation of parsing performance and lower quality of annotations in comparison with human-based annotations. Using sentences from the Penn Treebank WSJ, we also report systematically obtained inter-annotator agreement estimates for English dependency parsing. Our agreement results control for parser bias, and are consequential in that they are on par with state of the art parsing performance for English newswire. We discuss the impact of our findings on strategies for future annotation efforts and parser evaluations.

We present an approach to searching large video corpora for clips which depict a natural-language query in the form of a sentence. Compositional semantics is used to encode subtle meaning differences lost in other approaches, such as the difference between two sentences which have identical words but entirely different meaning: The person rode the horse versus The horse rode the person. Given a sentential query and a natural-language parser, we produce a score indicating how well a video clip depicts that sentence for each clip in a corpus and return a ranked list of clips. Two fundamental problems are addressed simultaneously: detecting and tracking objects, and recognizing whether those tracks depict the query. Because both tracking and object detection are unreliable, our approach uses the sentential query to focus the tracker on the relevant participants and ensures that the resulting tracks are described by the sentential query. While most earlier work was limited to single-word queries which correspond to either verbs or nouns, we search for complex queries which contain multiple phrases, such as prepositional phrases, and modifiers, such as adverbs. We demonstrate this approach by searching for 2,627 naturally elicited sentential queries in 10 Hollywood movies.

Understanding language goes hand in hand with the ability to integrate complex contextual information obtained via perception.In this work, we present a novel task for grounded language understanding: disambiguating a sentence given a visual scene which depicts one of the possible interpretations of that sentence.To this end, we introduce a new multimodal corpus containing ambiguous sentences, representing a wide range of syntactic, semantic and discourse ambiguities, coupled with videos that visualize the different interpretations for each sentence.We address this task by extending a vision model which determines if a sentence is depicted by a video.We demonstrate how such a model can be adjusted to recognize different interpretations of the same underlying sentence, allowing to disambiguate sentences in a unified fashion across the different ambiguity types.

We present an approach to simultaneously reasoning about a video clip and an entire natural-language sentence. The compositional nature of language is exploited to construct models which represent the meanings of entire sentences composed out of the meanings of the words in those sentences mediated by a grammar that encodes the predicate-argument relations. We demonstrate that these models faithfully represent the meanings of sentences and are sensitive to how the roles played by participants (nouns), their characteristics (adjectives), the actions performed (verbs), the manner of such actions (adverbs), and changing spatial relations between participants (prepositions) affect the meaning of a sentence and how it is grounded in video. We exploit this methodology in three ways. In the first, a video clip along with a sentence are taken as input and the participants in the event described by the sentence are highlighted, even when the clip depicts multiple similar simultaneous events. In the second, a video clip is taken as input without a sentence and a sentence is generated that describes an event in that clip. In the third, a corpus of video clips is paired with sentences which describe some of the events in those clips and the meanings of the words in those sentences are learned. We learn these meanings without needing to specify which attribute of the video clips each word in a given sentence refers to. The learned meaning representations are shown to be intelligible to humans.

We present a system that demonstrates how the compositional structure of events, in concert with the compositional structure of language, can interplay with the underlying focusing mechanisms in video action recognition, providing a medium for top-down and bottom-up integration as well as multi-modal integration between vision and language. We show how the roles played by participants (nouns), their characteristics (adjectives), the actions performed (verbs), the manner of such actions (adverbs), and changing spatial relations between participants (prepositions), in the form of whole-sentence descriptions mediated by a grammar, guides the activity-recognition process. Further, the utility and expressiveness of our framework is demonstrated by performing three separate tasks in the domain of multi-activity video: sentence-guided focus of attention, generation of sentential description, and query-based search, simply by leveraging the framework in different manners.

Recognizing human activities in partially observed videos is a challenging problem and has many practical applications. When the unobserved subsequence is at the end of the video, the problem is reduced to activity prediction from unfinished activity streaming, which has been studied by many researchers. However, in the general case, an unobserved subsequence may occur at any time by yielding a temporal gap in the video. In this paper, we propose a new method that can recognize human activities from partially observed videos in the general case. Specifically, we formulate the problem into a probabilistic framework: 1) dividing each activity into multiple ordered temporal segments, 2) using spatiotemporal features of the training video samples in each segment as bases and applying sparse coding (SC) to derive the activity likelihood of the test video sample at each segment, and 3) finally combining the likelihood at each segment to achieve a global posterior for the activities. We further extend the proposed method to include more bases that correspond to a mixture of segments with different temporal lengths (MSSC), which can better represent the activities with large intra-class variations. We evaluate the proposed methods (SC and MSSC) on various real videos. We also evaluate the proposed methods on two special cases: 1) activity prediction where the unobserved subsequence is at the end of the video, and 2) human activity recognition on fully observed videos. Experimental results show that the proposed methods outperform existing state-of-the-art comparison methods.

We present a generative domain of visual objects by analogy to the generative nature of human language. Just as small inventories of phonemes and words combine in a grammatical fashion to yield myriad valid words and utterances, a small inventory of physical parts combine in a grammatical fashion to yield myriad valid assemblies. We apply the notion of a language model from speech recognition to this visual domain to similarly improve the performance of the recognition process over what would be possible by only applying recognizers to the components. Unlike the context-free models for human language, our visual language models are context sensitive and formulated as stochastic constraint-satisfaction problems. And unlike the situation for human language where all components are observable, our methods deal with occlusion, successfully recovering object structure despite unobservable components. We demonstrate our system with an integrated robotic system for disassembling structures that performs whole-scene reconstruction consistent with a language model in the presence of noisy feature detectors.

We present an integrated vision and robotic system that plays, and learns to play, simple physically-instantiated board games that are variants of TIC TAC TOE and HEXA-PAWN. We employ novel custom vision and robotic hardware designed specifically for this learning task. The game rules can be parametrically specified. Two independent computational agents alternate playing the two opponents with the shared vision and robotic hardware, using pre-specified rule sets. A third independent computational agent, sharing the same hardware, learns the game rules solely by observing the physical play, without access to the pre-specified rule set, using inductive logic programming with minimal background knowledge possessed by human children. The vision component of our integrated system reliably detects the position of the board in the image and reconstructs the game state after every move, from a single image. The robotic component reliably moves pieces both between board positions and to and from off-board positions as needed by an arbitrary parametrically-specified legal-move generator. Thus the rules of games learned solely by observing physical play can drive further physical play. We demonstrate our system learning to play six different games.