In recent years, Multi-Agent Path Finding (MAPF) has attracted attention from the fields of both Operations Research (OR) and Reinforcement Learning (RL). However, in the 2021 Flatland3 Challenge, a competition on MAPF, the best RL method scored only 27.9, far less than the best OR method. This paper proposes a new RL solution to Flatland3 Challenge, which scores 125.3, several times higher than the best RL solution before. We creatively apply a novel network architecture, TreeLSTM, to MAPF in our solution. Together with several other RL techniques, including reward shaping, multiple-phase training, and centralized control, our solution is comparable to the top 2-3 OR methods.

安全已成为对现实世界系统应用深度加固学习的主要挑战之一。目前，诸如人类监督等外部知识的纳入唯一可以防止代理人访问灾难性状态的手段。在本文中，我们提出了一种基于安全模型的强化学习的新框架MBHI，可确保状态级安全，可以有效地避免“本地”和“非本地”灾难。监督学习者的合并在MBHI培训，以模仿人类阻止决策。类似于人类决策过程，MBHI将在执行对环境的动作之前在动态模型中推出一个想象的轨迹，并估算其安全性。当想象力遇到灾难时，MBHI将阻止当前的动作并使用高效的MPC方法来输出安全策略。我们在几个安全任务中评估了我们的方法，结果表明，与基线相比，MBHI在样品效率和灾难数方面取得了更好的性能。

Sign language recognition (SLR) aims to overcome the communication barrier for the people with deafness or the people with hard hearing. Most existing approaches can be typically divided into two lines, i.e., Skeleton-based and RGB-based methods, but both the two lines of methods have their limitations. RGB-based approaches usually overlook the fine-grained hand structure, while Skeleton-based methods do not take the facial expression into account. In attempts to address both limitations, we propose a new framework named Spatial-temporal Part-aware network (StepNet), based on RGB parts. As the name implies, StepNet consists of two modules: Part-level Spatial Modeling and Part-level Temporal Modeling. Particularly, without using any keypoint-level annotations, Part-level Spatial Modeling implicitly captures the appearance-based properties, such as hands and faces, in the feature space. On the other hand, Part-level Temporal Modeling captures the pertinent properties over time by implicitly mining the long-short term context. Extensive experiments show that our StepNet, thanks to Spatial-temporal modules, achieves competitive Top-1 Per-instance accuracy on three widely-used SLR benchmarks, i.e., 56.89% on WLASL, 77.2% on NMFs-CSL, and 77.1% on BOBSL. Moreover, the proposed method is compatible with the optical flow input, and can yield higher performance if fused. We hope that this work can serve as a preliminary step for the people with deafness.

Script is a kind of structured knowledge extracted from texts, which contains a sequence of events. Based on such knowledge, script event prediction aims to predict the subsequent event. To do so, two aspects should be considered for events, namely, event description (i.e., what the events should contain) and event encoding (i.e., how they should be encoded). Most existing methods describe an event by a verb together with only a few core arguments (i.e., subject, object, and indirect object), which are not precise. In addition, existing event encoders are limited to a fixed number of arguments, which are not flexible to deal with extra information. Thus, in this paper, we propose the Rich Event Prediction (REP) framework for script event prediction. Fundamentally, it is based on the proposed rich event description, which enriches the existing ones with three kinds of important information, namely, the senses of verbs, extra semantic roles, and types of participants. REP contains an event extractor to extract such information from texts. Based on the extracted rich information, a predictor then selects the most probable subsequent event. The core component of the predictor is a transformer-based event encoder to flexibly deal with an arbitrary number of arguments. Experimental results on the widely used Gigaword Corpus show the effectiveness of the proposed framework.

Recent progress on vision-language foundation models have brought significant advancement to building general-purpose robots. By using the pre-trained models to encode the scene and instructions as inputs for decision making, the instruction-conditioned policy can generalize across different objects and tasks. While this is encouraging, the policy still fails in most cases given an unseen task or environment. To adapt the policy to unseen tasks and environments, we explore a new paradigm on leveraging the pre-trained foundation models with Self-PLAY and Self-Describe (SPLAYD). When deploying the trained policy to a new task or a new environment, we first let the policy self-play with randomly generated instructions to record the demonstrations. While the execution could be wrong, we can use the pre-trained foundation models to accurately self-describe (i.e., re-label or classify) the demonstrations. This automatically provides new pairs of demonstration-instruction data for policy fine-tuning. We evaluate our method on a broad range of experiments with the focus on generalization on unseen objects, unseen tasks, unseen environments, and sim-to-real transfer. We show SPLAYD improves baselines by a large margin in all cases. Our project page is available at https://geyuying.github.io/SPLAYD/

We present the Group Propagation Vision Transformer (GPViT): a novel nonhierarchical (i.e. non-pyramidal) transformer model designed for general visual recognition with high-resolution features. High-resolution features (or tokens) are a natural fit for tasks that involve perceiving fine-grained details such as detection and segmentation, but exchanging global information between these features is expensive in memory and computation because of the way self-attention scales. We provide a highly efficient alternative Group Propagation Block (GP Block) to exchange global information. In each GP Block, features are first grouped together by a fixed number of learnable group tokens; we then perform Group Propagation where global information is exchanged between the grouped features; finally, global information in the updated grouped features is returned back to the image features through a transformer decoder. We evaluate GPViT on a variety of visual recognition tasks including image classification, semantic segmentation, object detection, and instance segmentation. Our method achieves significant performance gains over previous works across all tasks, especially on tasks that require high-resolution outputs, for example, our GPViT-L3 outperforms Swin Transformer-B by 2.0 mIoU on ADE20K semantic segmentation with only half as many parameters. Code and pre-trained models are available at https://github.com/ChenhongyiYang/GPViT .

This paper presents a new data augmentation algorithm for natural understanding tasks, called RPN:Random Position Noise algorithm.Due to the relative paucity of current text augmentation methods. Few of the extant methods apply to natural language understanding tasks for all sentence-level tasks.RPN applies the traditional augmentation on the original text to the word vector level. The RPN algorithm makes a substitution in one or several dimensions of some word vectors. As a result, the RPN can introduce a certain degree of perturbation to the sample and can adjust the range of perturbation on different tasks. The augmented samples are then used to give the model training.This makes the model more robust. In subsequent experiments, we found that adding RPN to the training or fine-tuning model resulted in a stable boost on all 8 natural language processing tasks, including TweetEval, CoLA, and SST-2 datasets, and more significant improvements than other data augmentation algorithms.The RPN algorithm applies to all sentence-level tasks for language understanding and is used in any deep learning model with a word embedding layer.

We revisit a simple Learning-from-Scratch baseline for visuo-motor control that uses data augmentation and a shallow ConvNet. We find that this baseline has competitive performance with recent methods that leverage frozen visual representations trained on large-scale vision datasets.

Poor sample efficiency continues to be the primary challenge for deployment of deep Reinforcement Learning (RL) algorithms for real-world applications, and in particular for visuo-motor control. Model-based RL has the potential to be highly sample efficient by concurrently learning a world model and using synthetic rollouts for planning and policy improvement. However, in practice, sample-efficient learning with model-based RL is bottlenecked by the exploration challenge. In this work, we find that leveraging just a handful of demonstrations can dramatically improve the sample-efficiency of model-based RL. Simply appending demonstrations to the interaction dataset, however, does not suffice. We identify key ingredients for leveraging demonstrations in model learning -- policy pretraining, targeted exploration, and oversampling of demonstration data -- which forms the three phases of our model-based RL framework. We empirically study three complex visuo-motor control domains and find that our method is 150%-250% more successful in completing sparse reward tasks compared to prior approaches in the low data regime (100K interaction steps, 5 demonstrations). Code and videos are available at: https://nicklashansen.github.io/modemrl

For the aerial manipulator that performs aerial work tasks, the actual operating environment it faces is very complex, and it is affected by internal and external multi-source disturbances. In this paper, to effectively improve the anti-disturbance control performance of the aerial manipulator, an adaptive neural network backstepping control method based on variable inertia parameter modeling is proposed. Firstly, for the intense internal coupling disturbance, we analyze and model it from the perspective of the generation mechanism of the coupling disturbance, and derive the dynamics model of the aerial manipulator system and the coupling disturbance model based on the variable inertia parameters. Through the proposed coupling disturbance model, we can compensate the strong coupling disturbance in a way of feedforward. Then, the adaptive neural network is proposed and applid to estimate and compensate the additional disturbances, and the closed-loop controller is designed based on the backstepping control method. Finally, we verify the correctness of the proposed coupling disturbance model through physical experiment under a large range motion of the manipulator. Two sets of comparative simulation results also prove the accurate estimation of the proposed adaptive neural network for additional disturbances and the effectiveness and superiority of the proposed control method.