Alexa, play with robot: Introducing the First Alexa Prize SimBot Challenge on Embodied AI

The Alexa Prize program has empowered numerous university students to explore, experiment, and showcase their talents in building conversational agents through challenges like the SocialBot Grand Challenge and the TaskBot Challenge. As conversational agents increasingly appear in multimodal and embodied contexts, it is important to explore the affordances of conversational interaction augmented with computer vision and physical embodiment. This paper describes the SimBot Challenge, a new challenge in which university teams compete to build robot assistants that complete tasks in a simulated physical environment. This paper provides an overview of the SimBot Challenge, which included both online and offline challenge phases. We describe the infrastructure and support provided to the teams including Alexa Arena, the simulated environment, and the ML toolkit provided to teams to accelerate their building of vision and language models. We summarize the approaches the participating teams took to overcome research challenges and extract key lessons learned. Finally, we provide analysis of the performance of the competing SimBots during the competition.

RT-2: Vision-Language-Action Models Transfer Web Knowledge to Robotic Control

We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control to boost generalization and enable emergent semantic reasoning. Our goal is to enable a single end-to-end trained model to both learn to map robot observations to actions and enjoy the benefits of large-scale pretraining on language and vision-language data from the web. To this end, we propose to co-fine-tune state-of-the-art vision-language models on both robotic trajectory data and Internet-scale vision-language tasks, such as visual question answering. In contrast to other approaches, we propose a simple, general recipe to achieve this goal: in order to fit both natural language responses and robotic actions into the same format, we express the actions as text tokens and incorporate them directly into the training set of the model in the same way as natural language tokens. We refer to such category of models as vision-language-action models (VLA) and instantiate an example of such a model, which we call RT-2. Our extensive evaluation (6k evaluation trials) shows that our approach leads to performant robotic policies and enables RT-2 to obtain a range of emergent capabilities from Internet-scale training. This includes significantly improved generalization to novel objects, the ability to interpret commands not present in the robot training data (such as placing an object onto a particular number or icon), and the ability to perform rudimentary reasoning in response to user commands (such as picking up the smallest or largest object, or the one closest to another object). We further show that incorporating chain of thought reasoning allows RT-2 to perform multi-stage semantic reasoning, for example figuring out which object to pick up for use as an improvised hammer (a rock), or which type of drink is best suited for someone who is tired (an energy drink).

Event Detection from Social Media Stream: Methods, Datasets and Opportunities

Social media streams contain large and diverse amount of information, ranging from daily-life stories to the latest global and local events and news. Twitter, especially, allows a fast spread of events happening real time, and enables individuals and organizations to stay informed of the events happening now. Event detection from social media data poses different challenges from traditional text and is a research area that has attracted much attention in recent years. In this paper, we survey a wide range of event detection methods for Twitter data stream, helping readers understand the recent development in this area. We present the datasets available to the public. Furthermore, a few research opportunities

Exploring Inductive Biases in Contrastive Learning: A Clustering Perspective

This paper investigates the differences in data organization between contrastive and supervised learning methods, focusing on the concept of locally dense clusters. We introduce a novel metric, Relative Local Density (RLD), to quantitatively measure local density within clusters. Visual examples are provided to highlight the distinctions between locally dense clusters and globally dense ones. By comparing the clusters formed by contrastive and supervised learning, we reveal that contrastive learning generates locally dense clusters without global density, while supervised learning creates clusters with both local and global density. We further explore the use of a Graph Convolutional Network (GCN) classifier as an alternative to linear classifiers for handling locally dense clusters. Finally, we utilize t-SNE visualizations to substantiate the differences between the features generated by contrastive and supervised learning methods. We conclude by proposing future research directions, including the development of efficient classifiers tailored to contrastive learning and the creation of innovative augmentation algorithms.

Deep RL at Scale: Sorting Waste in Office Buildings with a Fleet of Mobile Manipulators

We describe a system for deep reinforcement learning of robotic manipulation skills applied to a large-scale real-world task: sorting recyclables and trash in office buildings. Real-world deployment of deep RL policies requires not only effective training algorithms, but the ability to bootstrap real-world training and enable broad generalization. To this end, our system combines scalable deep RL from real-world data with bootstrapping from training in simulation, and incorporates auxiliary inputs from existing computer vision systems as a way to boost generalization to novel objects, while retaining the benefits of end-to-end training. We analyze the tradeoffs of different design decisions in our system, and present a large-scale empirical validation that includes training on real-world data gathered over the course of 24 months of experimentation, across a fleet of 23 robots in three office buildings, with a total training set of 9527 hours of robotic experience. Our final validation also consists of 4800 evaluation trials across 240 waste station configurations, in order to evaluate in detail the impact of the design decisions in our system, the scaling effects of including more real-world data, and the performance of the method on novel objects. The projects website and videos can be found at \href{http://rl-at-scale.github.io}{rl-at-scale.github.io}.

Spatiotemporal and Semantic Zero-inflated Urban Anomaly Prediction

Urban anomaly predictions, such as traffic accident prediction and crime prediction, are of vital importance to smart city security and maintenance. Existing methods typically use deep learning to capture the intra-dependencies in spatial and temporal dimensions. However, numerous key challenges remain unsolved, for instance, sparse zero-inflated data due to urban anomalies occurring with low frequency (which can lead to poor performance on real-world datasets), and both intra- and inter-dependencies of abnormal patterns across spatial, temporal, and semantic dimensions. Moreover, a unified approach to predict multiple kinds of anomaly is left to explore. In this paper, we propose STS to jointly capture the intra- and inter-dependencies between the patterns and the influential factors in three dimensions. Further, we use a multi-task prediction module with a customized loss function to solve the zero-inflated issue. To verify the effectiveness of the model, we apply it to two urban anomaly prediction tasks, crime prediction and traffic accident risk prediction, respectively. Experiments on two application scenarios with four real-world datasets demonstrate the superiority of STS, which outperforms state-of-the-art methods in the mean absolute error and the root mean square error by 37.88% and 18.10% on zero-inflated datasets, and, 60.32% and 37.28% on non-zero datasets, respectively.

SR-init: An interpretable layer pruning method

Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible solution to the aforementioned challenges. However, the interpretation of existing pruning criteria is always overlooked. To counter this issue, we propose a novel layer pruning method by exploring the Stochastic Re-initialization. Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers. On the basis of this observation, we come up with a layer pruning criterion, i.e., those layers that are not sensitive to stochastic re-initialization (low accuracy drop) produce less contribution to the model and could be pruned with acceptable loss. Afterward, we experimentally verify the interpretability of SR-init via feature visualization. The visual explanation demonstrates that SR-init is theoretically feasible, thus we compare it with state-of-the-art methods to further evaluate its practicability. As for ResNet56 on CIFAR-10 and CIFAR-100, SR-init achieves a great reduction in parameters (63.98% and 37.71%) with an ignorable drop in top-1 accuracy (-0.56% and 0.8%). With ResNet50 on ImageNet, we achieve a 15.59% FLOPs reduction by removing 39.29% of the parameters, with only a drop of 0.6% in top-1 accuracy. Our code is available at https://github.com/huitang-zjut/SR-init.

Sr-init: An interpretable layer pruning method

Despite the popularization of deep neural networks (DNNs) in many fields, it is still challenging to deploy state-of-the-art models to resource-constrained devices due to high computational overhead. Model pruning provides a feasible solution to the aforementioned challenges. However, the interpretation of existing pruning criteria is always overlooked. To counter this issue, we propose a novel layer pruning method by exploring the Stochastic Re-initialization. Our SR-init method is inspired by the discovery that the accuracy drop due to stochastic re-initialization of layer parameters differs in various layers. On the basis of this observation, we come up with a layer pruning criterion, i.e., those layers that are not sensitive to stochastic re-initialization (low accuracy drop) produce less contribution to the model and could be pruned with acceptable loss. Afterward, we experimentally verify the interpretability of SR-init via feature visualization. The visual explanation demonstrates that SR-init is theoretically feasible, thus we compare it with state-of-the-art methods to further evaluate its practicability. As for ResNet56 on CIFAR-10 and CIFAR-100, SR-init achieves a great reduction in parameters (63.98% and 37.71%) with an ignorable drop in top-1 accuracy (-0.56% and 0.8%). With ResNet50 on ImageNet, we achieve a 15.59% FLOPs reduction by removing 39.29% of the parameters, with only a drop of 0.6% in top-1 accuracy. Our code is available at https://github.com/huitang-zjut/SRinit.

Open-World Object Manipulation using Pre-trained Vision-Language Models

For robots to follow instructions from people, they must be able to connect the rich semantic information in human vocabulary, e.g. "can you get me the pink stuffed whale?" to their sensory observations and actions. This brings up a notably difficult challenge for robots: while robot learning approaches allow robots to learn many different behaviors from first-hand experience, it is impractical for robots to have first-hand experiences that span all of this semantic information. We would like a robot's policy to be able to perceive and pick up the pink stuffed whale, even if it has never seen any data interacting with a stuffed whale before. Fortunately, static data on the internet has vast semantic information, and this information is captured in pre-trained vision-language models. In this paper, we study whether we can interface robot policies with these pre-trained models, with the aim of allowing robots to complete instructions involving object categories that the robot has never seen first-hand. We develop a simple approach, which we call Manipulation of Open-World Objects (MOO), which leverages a pre-trained vision-language model to extract object-identifying information from the language command and image, and conditions the robot policy on the current image, the instruction, and the extracted object information. In a variety of experiments on a real mobile manipulator, we find that MOO generalizes zero-shot to a wide range of novel object categories and environments. In addition, we show how MOO generalizes to other, non-language-based input modalities to specify the object of interest such as finger pointing, and how it can be further extended to enable open-world navigation and manipulation. The project's website and evaluation videos can be found at https://robot-moo.github.io/

Grounded Decoding: Guiding Text Generation with Grounded Models for Robot Control

Recent progress in large language models (LLMs) has demonstrated the ability to learn and leverage Internet-scale knowledge through pre-training with autoregressive models. Unfortunately, applying such models to settings with embodied agents, such as robots, is challenging due to their lack of experience with the physical world, inability to parse non-language observations, and ignorance of rewards or safety constraints that robots may require. On the other hand, language-conditioned robotic policies that learn from interaction data can provide the necessary grounding that allows the agent to be correctly situated in the real world, but such policies are limited by the lack of high-level semantic understanding due to the limited breadth of the interaction data available for training them. Thus, if we want to make use of the semantic knowledge in a language model while still situating it in an embodied setting, we must construct an action sequence that is both likely according to the language model and also realizable according to grounded models of the environment. We frame this as a problem similar to probabilistic filtering: decode a sequence that both has high probability under the language model and high probability under a set of grounded model objectives. We demonstrate this guided decoding strategy is able to solve complex, long-horizon embodiment tasks in a robotic setting by leveraging the knowledge of both models. The project's website can be found at grounded-decoding.github.io.