Search

We demonstrate experimental results with LLMs that address robotics task planning problems. Recently, LLMs have been applied in robotics task planning, particularly using a code generation approach that converts complex high-level instructions into mid-level policy codes. In contrast, our approach acquires text descriptions of the task and scene objects, then formulates task planning through natural language reasoning, and outputs coordinate level control commands, thus reducing the necessity for intermediate representation code as policies with pre-defined APIs. Our approach is evaluated on a multi-modal prompt simulation benchmark, demonstrating that our prompt engineering experiments with natural language reasoning significantly enhance success rates compared to its absence. Furthermore, our approach illustrates the potential for natural language descriptions to transfer robotics skills from known tasks to previously unseen tasks. The project website: https://natural-language-as-policies.github.io, Comment: 8 pages, 2 figures

Behavioral cloning uses a dataset of demonstrations to learn a policy. To overcome computationally expensive training procedures and address the policy adaptation problem, we propose to use latent spaces of pre-trained foundation models to index a demonstration dataset, instantly access similar relevant experiences, and copy behavior from these situations. Actions from a selected similar situation can be performed by the agent until representations of the agent's current situation and the selected experience diverge in the latent space. Thus, we formulate our control problem as a dynamic search problem over a dataset of experts' demonstrations. We test our approach on BASALT MineRL-dataset in the latent representation of a Video Pre-Training model. We compare our model to state-of-the-art, Imitation Learning-based Minecraft agents. Our approach can effectively recover meaningful demonstrations and show human-like behavior of an agent in the Minecraft environment in a wide variety of scenarios. Experimental results reveal that performance of our search-based approach clearly wins in terms of accuracy and perceptual evaluation over learning-based models.

Recent advancements in Generative Artificial Intelligence, particularly in the realm of Large Language Models (LLMs) and Large Vision Language Models (LVLMs), have enabled the prospect of leveraging cognitive planners within robotic systems. This work focuses on solving the object goal navigation problem by mimicking human cognition to attend, perceive and store task specific information and generate plans with the same. We introduce a comprehensive framework capable of exploring an unfamiliar environment in search of an object by leveraging the capabilities of Large Language Models(LLMs) and Large Vision Language Models (LVLMs) in understanding the underlying semantics of our world. A challenging task in using LLMs to generate high level sub-goals is to efficiently represent the environment around the robot. We propose to use a 3D scene modular representation, with semantically rich descriptions of the object, to provide the LLM with task relevant information. But providing the LLM with a mass of contextual information (rich 3D scene semantic representation), can lead to redundant and inefficient plans. We propose to use an LLM based pruner that leverages the capabilities of in-context learning to prune out irrelevant goal specific information.

Diffusion generative models have recently become a robust technique for producing and modifying coherent, high-quality video. This survey offers a systematic overview of critical elements of diffusion models for video generation, covering applications, architectural choices, and the modeling of temporal dynamics. Recent advancements in the field are summarized and grouped into development trends. The survey concludes with an overview of remaining challenges and an outlook on the future of the field. Website: https://github.com/ndrwmlnk/Awesome-Video-Diffusion-Models

The lane graph is a key component for building high-definition (HD) maps and crucial for downstream tasks such as autonomous driving or navigation planning. Previously, He et al. (2022) explored the extraction of the lane-level graph from aerial imagery utilizing a segmentation based approach. However, segmentation networks struggle to achieve perfect segmentation masks resulting in inaccurate lane graph extraction. We explore additional enhancements to refine this segmentation-based approach and extend it with a diffusion probabilistic model (DPM) component. This combination further improves the GEO F1 and TOPO F1 scores, which are crucial indicators of the quality of a lane graph, in the undirected graph in non-intersection areas. We conduct experiments on a publicly available dataset, demonstrating that our method outperforms the previous approach, particularly in enhancing the connectivity of such a graph, as measured by the TOPO F1 score. Moreover, we perform ablation studies on the individual components of our method to understand their contribution and evaluate their effectiveness.

In this paper, we introduce a method for unifying language, action, and state information in a shared embedding space to facilitate a range of downstream tasks in robot learning. Our method, Contrastive Language, Action, and State Pre-training (CLASP), extends the CLIP formulation by incorporating distributional learning, capturing the inherent complexities and one-to-many relationships in behaviour-text alignment. By employing distributional outputs for both text and behaviour encoders, our model effectively associates diverse textual commands with a single behaviour and vice-versa. We demonstrate the utility of our method for the following downstream tasks: zero-shot text-behaviour retrieval, captioning unseen robot behaviours, and learning a behaviour prior for language-conditioned reinforcement learning. Our distributional encoders exhibit superior retrieval and captioning performance on unseen datasets, and the ability to generate meaningful exploratory behaviours from textual commands, capturing the intricate relationships between language, action, and state. This work represents an initial step towards developing a unified pre-trained model for robotics, with the potential to generalise to a broad range of downstream tasks.

In this paper, we compare methods for estimating the complexity of two-dimensional shapes and introduce a method that exploits reconstruction loss of Variational Autoencoders with different sizes of latent vectors. Although complexity of a shape is not a well defined attribute, different aspects of it can be estimated. We demonstrate that our methods captures some aspects of shape complexity. Code and training details will be publicly available.

To facilitate research in the direction of fine-tuning foundation models from human feedback, we held the MineRL BASALT Competition on Fine-Tuning from Human Feedback at NeurIPS 2022. The BASALT challenge asks teams to compete to develop algorithms to solve tasks with hard-to-specify reward functions in Minecraft. Through this competition, we aimed to promote the development of algorithms that use human feedback as channels to learn the desired behavior. We describe the competition and provide an overview of the top solutions. We conclude by discussing the impact of the competition and future directions for improvement.

Physical reasoning is a crucial aspect in the development of general AI systems, given that human learning starts with interacting with the physical world before progressing to more complex concepts. Although researchers have studied and assessed the physical reasoning of AI approaches through various specific benchmarks, there is no comprehensive approach to evaluating and measuring progress. Therefore, we aim to offer an overview of existing benchmarks and their solution approaches and propose a unified perspective for measuring the physical reasoning capacity of AI systems. We select benchmarks that are designed to test algorithmic performance in physical reasoning tasks. While each of the selected benchmarks poses a unique challenge, their ensemble provides a comprehensive proving ground for an AI generalist agent with a measurable skill level for various physical reasoning concepts. This gives an advantage to such an ensemble of benchmarks over other holistic benchmarks that aim to simulate the real world by intertwining its complexity and many concepts. We group the presented set of physical reasoning benchmarks into subcategories so that more narrow generalist AI agents can be tested first on these groups.

This report introduces our UniTeam agent - an improved baseline for the "HomeRobot: Open Vocabulary Mobile Manipulation" challenge. The challenge poses problems of navigation in unfamiliar environments, manipulation of novel objects, and recognition of open-vocabulary object classes. This challenge aims to facilitate cross-cutting research in embodied AI using recent advances in machine learning, computer vision, natural language, and robotics. In this work, we conducted an exhaustive evaluation of the provided baseline agent; identified deficiencies in perception, navigation, and manipulation skills; and improved the baseline agent's performance. Notably, enhancements were made in perception - minimizing misclassifications; navigation - preventing infinite loop commitments; picking - addressing failures due to changing object visibility; and placing - ensuring accurate positioning for successful object placement.

Reinforcement learning and Imitation Learning approaches utilize policy learning strategies that are difficult to generalize well with just a few examples of a task. In this work, we propose a language-conditioned semantic search-based method to produce an online search-based policy from the available demonstration dataset of state-action trajectories. Here we directly acquire actions from the most similar manipulation trajectories found in the dataset. Our approach surpasses the performance of the baselines on the CALVIN benchmark and exhibits strong zero-shot adaptation capabilities. This holds great potential for expanding the use of our online search-based policy approach to tasks typically addressed by Imitation Learning or Reinforcement Learning-based policies.

Behavioural cloning uses a dataset of demonstrations to learn a behavioural policy. To overcome various learning and policy adaptation problems, we propose to use latent space to index a demonstration dataset, instantly access similar relevant experiences, and copy behavior from these situations. Actions from a selected similar situation can be performed by the agent until representations of the agent's current situation and the selected experience diverge in the latent space. Thus, we formulate our control problem as a search problem over a dataset of experts' demonstrations. We test our approach on BASALT MineRL-dataset in the latent representation of a Video PreTraining model. We compare our model to state-of-the-art Minecraft agents. Our approach can effectively recover meaningful demonstrations and show human-like behavior of an agent in the Minecraft environment in a wide variety of scenarios. Experimental results reveal that performance of our search-based approach is comparable to trained models, while allowing zero-shot task adaptation by changing the demonstration examples.

In the last few years, artistic image-making with deep learning models has gained a considerable amount of traction. A large number of these models operate directly in the pixel space and generate raster images. This is however not how most humans would produce artworks, for example, by planning a sequence of shapes and strokes to draw. Recent developments in deep learning methods help to bridge the gap between stroke-based paintings and pixel photo generation. With this survey, we aim to provide a structured introduction and understanding of common challenges and approaches in stroke-based rendering algorithms. These algorithms range from simple rule-based heuristics to stroke optimization and deep reinforcement agents, trained to paint images with differentiable vector graphics and neural rendering.

Our aim is to build autonomous agents that can solve tasks in environments like Minecraft. To do so, we used an imitation learning-based approach. We formulate our control problem as a search problem over a dataset of experts' demonstrations, where the agent copies actions from a similar demonstration trajectory of image-action pairs. We perform a proximity search over the BASALT MineRL-dataset in the latent representation of a Video PreTraining model. The agent copies the actions from the expert trajectory as long as the distance between the state representations of the agent and the selected expert trajectory from the dataset do not diverge. Then the proximity search is repeated. Our approach can effectively recover meaningful demonstration trajectories and show human-like behavior of an agent in the Minecraft environment.

Our goal with this survey is to provide an overview of the state of the art deep learning methods for face generation and editing using StyleGAN. The survey covers the evolution of StyleGAN, from PGGAN to StyleGAN3, and explores relevant topics such as suitable metrics for training, different latent representations, GAN inversion to latent spaces of StyleGAN, face image editing, cross-domain face stylization, face restoration, and even Deepfake applications. We aim to provide an entry point into the field for readers that have basic knowledge about the field of deep learning and are looking for an accessible introduction and overview.

Learn-to-Race Autonomous Racing Virtual Challenge hosted on wwwaicrowdcom platform consisted of two tracks: Single and Multi Camera. Our UniTeam team was among the final winners in the Single Camera track. The agent is required to pass the previously unknown F1-style track in the minimum time with the least amount of off-road driving violations. In our approach, we used the U-Net architecture for road segmentation, variational autocoder for encoding a road binary mask, and a nearest-neighbor search strategy that selects the best action for a given state. Our agent achieved an average speed of 105 km/h on stage 1 (known track) and 73 km/h on stage 2 (unknown track) without any off-road driving violations. Here we present our solution and results., Comment: Published in SL4AD Workshop, ICML 2022

The practical application of learning agents requires sample efficient and interpretable algorithms. Learning from behavioral priors is a promising way to bootstrap agents with a better-than-random exploration policy or a safe-guard against the pitfalls of early learning. Existing solutions for imitation learning require a large number of expert demonstrations and rely on hard-to-interpret learning methods like Deep Q-learning. In this work we present a planning-based approach that can use these behavioral priors for effective exploration and learning in a reinforcement learning environment, and we demonstrate that curated exploration policies in the form of behavioral priors can help an agent learn faster., Comment: Published in ICRA 2022 BPRL Workshop

AI Blitz XIII Faces challenge hosted on www.aicrowd.com platform consisted of five problems: Sentiment Classification, Age Prediction, Mask Prediction, Face Recognition, and Face De-Blurring. Our team GLaDOS took second place. Here we present our solutions and results. Code implementation: https://github.com/ndrwmlnk/ai-blitz-xiii

The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 10^12 GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input., Comment: Pre-print under review, submitted to Proceedings of Machine Learning Research

Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintain a steady flow. A way to represent traffic data is in the form of temporally changing heatmaps visualizing attributes of traffic, such as speed and volume. In recent works, U-Net models have shown SOTA performance on traffic forecasting from heatmaps. We propose to combine the U-Net architecture with graph layers which improves spatial generalization to unseen road networks compared to a Vanilla U-Net. In particular, we specialize existing graph operations to be sensitive to geographical topology and generalize pooling and upsampling operations to be applicable to graphs., Comment: About to be published in IJCNN Proceedings 2022

With this work we are explaining the "You Only Look Once" (YOLO) single-stage object detection approach as a parallel classification of 10647 fixed region proposals. We support this view by showing that each of YOLOs output pixel is attentive to a specific sub-region of previous layers, comparable to a local region proposal. This understanding reduces the conceptual gap between YOLO-like single-stage object detection models, RCNN-like two-stage region proposal based models, and ResNet-like image classification models. In addition, we created interactive exploration tools for a better visual understanding of the YOLO information processing streams: https://limchr.github.io/yolo_visualization

This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic’s score of a high score image and increase the critic’s score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://rebrand.ly/critic-guided-segmentation.

This work discusses a learning approach to mask rewarding objects in images using sparse reward signals from an imitation learning dataset. For that, we train an Hourglass network using only feedback from a critic model. The Hourglass network learns to produce a mask to decrease the critic's score of a high score image and increase the critic's score of a low score image by swapping the masked areas between these two images. We trained the model on an imitation learning dataset from the NeurIPS 2020 MineRL Competition Track, where our model learned to mask rewarding objects in a complex interactive 3D environment with a sparse reward signal. This approach was part of the 1st place winning solution in this competition. Video demonstration and code: https://rebrand.ly/critic-guided-segmentation

Reinforcement learning competitions have formed the basis for standard research benchmarks, galvanized advances in the state-of-the-art, and shaped the direction of the field. Despite this, a majority of challenges suffer from the same fundamental problems: participant solutions to the posed challenge are usually domain-specific, biased to maximally exploit compute resources, and not guaranteed to be reproducible. In this paper, we present a new framework of competition design that promotes the development of algorithms that overcome these barriers. We propose four central mechanisms for achieving this end: submission retraining, domain randomization, desemantization through domain obfuscation, and the limitation of competition compute and environment-sample budget. To demonstrate the efficacy of this design, we proposed, organized, and ran the MineRL 2020 Competition on Sample-Efficient Reinforcement Learning. In this work, we describe the organizational outcomes of the competition and show that the resulting participant submissions are reproducible, non-specific to the competition environment, and sample/resource efficient, despite the difficult competition task., Comment: 20 pages, several figures, published PMLR

We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular structure is motivated by hypothesizing a sequence of intuitive steps that humans apply when trying to solve such a task. The model first predicts the path the target object would follow without intervention and the path the target object should follow in order to solve the task. Next, it predicts the desired path of the action object and generates the placement of the action object. All components of the model are trained jointly in a supervised way; each component receives its own learning signal but learning signals are also backpropagated through the entire architecture. To evaluate the model we use PHYRE - a benchmark test for goal-driven physical reasoning in 2D mechanics puzzles., Comment: 1st NeurIPS workshop on Interpretable Inductive Biases and Physically Structured Learning (2020)

Deep Reinforcement Learning techniques demonstrate exciting results in robotic applications such as dexterous inhand manipulation. One of the challenging factors which come into play when performing real-world tasks is a combination of different sensory modalities (vision, preconception, and haptic) which support each other for identification of the position and orientation of the manipulated object. This mutual support is important when some of the modalities are occluded or noisy. Furthermore, update rates of different sensory modalities may not match each other. While we assume that vision alone can determine the state perfectly, it suffers from slow update rates and it is susceptible to dropout due to visual occlusion (eg palm over the object). On the other hand, haptic by means of touch and proprioceptive information is always present with a high update rate but suffers from ambiguous perception (eg the cube in Fig. 1 can take various possible orientations without a change in the haptic and proprioceptive perception). Therefore, we present an approach to infer the state of the object through a unified, synchronized, multisensory perception of position and orientation of a manipulated object. Our approach builds upon the recent work of learning dexterous in-hand manipulation [1], where an agent with a model-free policy was able to learn complex in-hand manipulation tasks using proprioceptive and touch feedback plus visual information about the manipulated object. In this work, the agent can perform vision-based object reorientation on a physical Shadow-Hand in a simulated environment. However, pose reconstruction of a manipulated …

Complex environments and tasks pose a difficult problem for holistic end-to-end learning approaches. Decomposition of an environment into interacting controllable and non-controllable objects allows supervised learning for non-controllable objects and universal value function approximator learning for controllable objects. Such decomposition should lead to a shorter learning time and better generalisation capability. Here, we consider arcade-game environments as sets of interacting objects (controllable, non-controllable) and propose a set of functional modules that are specialized on mastering different types of interactions in a broad range of environments. The modules utilize regression, supervised learning, and reinforcement learning algorithms. Results of this case study in different Atari games suggest that human-level performance can be achieved by a learning agent within a human amount of game experience (10-15 minutes game time) when a proper decomposition of an environment or a task is provided. However, automatization of such decomposition remains a challenging problem. This case study shows how a model of a causal structure underlying an environment or a task can benefit learning time and generalization capability of the agent, and argues in favor of exploiting modular structure in contrast to using pure end-to-end learning approaches.

In the NIPS 2017 Learning to Run challenge, participants were tasked with building a controller for a musculoskeletal model to make it run as fast as possible through an obstacle course. Top participants were invited to describe their algorithms. In this work, we present eight solutions that used deep reinforcement learning approaches, based on algorithms such as Deep Deterministic Policy Gradient, Proximal Policy Optimization, and Trust Region Policy Optimization. Many solutions use similar relaxations and heuristics, such as reward shaping, frame skipping, discretization of the action space, symmetry, and policy blending. However, each of the eight teams implemented different modifications of the known algorithms., Comment: 27 pages, 17 figures