论文检索

Reinforcement Learning

Yanjie Ze, Yuyao Liu, Ruizhe Shi, Jiaxin Qin, Zhecheng Yuan, Jiashun Wang, Huazhe Xu

Human hands possess remarkable dexterity and have long served as a source of inspiration for robotic manipulation. In this work, we propose a human $\textbf{H}$and-$\textbf{In}$formed visual representation learning framework to solve difficult $\textbf{Dex}$terous manipulation tasks ($\textbf{H-InDex}$) with reinforcement learning. Our framework consists of three stages: $\textit{(i)}$ pre-training representations with 3D human hand pose estimation, $\textit{(ii)}$ offline adapting representations with self-supervised keypoint detection, and $\textit{(iii)}$ reinforcement learning with exponential moving average BatchNorm. The last two stages only modify $0.36$% parameters of the pre-trained representation in total, ensuring the knowledge from pre-training is maintained to the full extent. We empirically study $\textbf{12}$ challenging dexterous manipulation tasks and find that $\textbf{H-InDex}$ largely surpasses strong baseline methods and the recent visual foundation models for motor control. Code and videos are available at https://yanjieze.com/H-InDex .

Reinforcement Learning

Sizhe Yang, Yanjie Ze, Huazhe Xu

Visual Reinforcement Learning (RL) agents trained on limited views face significant challenges in generalizing their learned abilities to unseen views. This inherent difficulty is known as the problem of $\textit{view generalization}$. In this work, we systematically categorize this fundamental problem into four distinct and highly challenging scenarios that closely resemble real-world situations. Subsequently, we propose a straightforward yet effective approach to enable successful adaptation of visual $\textbf{Mo}$del-based policies for $\textbf{Vie}$w generalization ($\textbf{MoVie}$) during test time, without any need for explicit reward signals and any modification during training time. Our method demonstrates substantial advancements across all four scenarios encompassing a total of $\textbf{18}$ tasks sourced from DMControl, xArm, and Adroit, with a relative improvement of $\mathbf{33}$%, $\mathbf{86}$%, and $\mathbf{152}$% respectively. The superior results highlight the immense potential of our approach for real-world robotics applications. Code and videos are available at https://yangsizhe.github.io/MoVie/.

Applications/Computer Vision

Yuanze Wang, Yichao Yan, Dianxi Shi, Wenhan Zhu, Jianqiang Xia, Tan Jeff, Songchang Jin, KE GAO, XIAOBO LI, Xiaokang Yang

Visual localization is a fundamental task in computer vision and robotics. Training existing visual localization methods requires a large number of posed images to generalize to novel views, while state-of-the-art methods generally require dense ground truth 3D labels for supervision. However, acquiring a large number of posed images and dense 3D labels in the real world is challenging and costly. In this paper, we present a novel visual localization method that achieves accurate localization while using only a few posed images compared to other localization methods. To achieve this, we first use a few posed images with coarse pseudo-3D labels provided by NeRF to train a coordinate regression network. Then a coarse pose is estimated from the regression network with PNP. Finally, we use the image-based visual servo (IBVS) with the scene prior provided by NeRF for pose optimization. Furthermore, our method can provide effective navigation prior, which enable navigation based on IBVS without using custom markers and depth sensor. Extensive experiments on 7-Scenes and 12-Scenes datasets demonstrate that our method outperforms state-of-the-art methods under the same setting, with only 5\% to 25\% training data. Furthermore, our framework can be naturally extended to the visual navigation task based on IBVS, and its effectiveness is verified in simulation experiments.

Applications/Robotics

Denis Blessing, Onur Celik, Xiaogang Jia, Moritz Reuss, Maximilian Li, Rudolf Lioutikov, Gerhard Neumann

Imitation learning uses data for training policies to solve complex tasks. However,when the training data is collected from human demonstrators, it often leadsto multimodal distributions because of the variability in human actions. Mostimitation learning methods rely on a maximum likelihood (ML) objective to learna parameterized policy, but this can result in suboptimal or unsafe behavior dueto the mode-averaging property of the ML objective. In this work, we proposeInformation Maximizing Curriculum, a curriculum-based approach that assignsa weight to each data point and encourages the model to specialize in the data itcan represent, effectively mitigating the mode-averaging problem by allowing themodel to ignore data from modes it cannot represent. To cover all modes and thus,enable versatile behavior, we extend our approach to a mixture of experts (MoE)policy, where each mixture component selects its own subset of the training datafor learning. A novel, maximum entropy-based objective is proposed to achievefull coverage of the dataset, thereby enabling the policy to encompass all modeswithin the data distribution. We demonstrate the effectiveness of our approach oncomplex simulated control tasks using versatile human demonstrations, achievingsuperior performance compared to state-of-the-art methods.

Shenao Zhang, Boyi Liu, Zhaoran Wang, Tuo Zhao

ReParameterization (RP) Policy Gradient Methods (PGMs) have been widely adopted for continuous control tasks in robotics and computer graphics. However, recent studies have revealed that, when applied to long-term reinforcement learning problems, model-based RP PGMs may experience chaotic and non-smooth optimization landscapes with exploding gradient variance, which leads to slow convergence. This is in contrast to the conventional belief that reparameterization methods have low gradient estimation variance in problems such as training deep generative models. To comprehend this phenomenon, we conduct a theoretical examination of model-based RP PGMs and search for solutions to the optimization difficulties. Specifically, we analyze the convergence of the model-based RP PGMs and pinpoint the smoothness of function approximators as a major factor that affects the quality of gradient estimation. Based on our analysis, we propose a spectral normalization method to mitigate the exploding variance issue caused by long model unrolls. Our experimental results demonstrate that proper normalization significantly reduces the gradient variance of model-based RP PGMs. As a result, the performance of the proposed method is comparable or superior to other gradient estimators, such as the Likelihood Ratio (LR) gradient estimator. Our code is available at https://github.com/agentification/RP_PGM.

Applications/Robotics

Jong Wook Bae, Jungho Kim, Junyong Yun, Changwon Kang, Jeongseon Choi, Chanhyeok Kim, Junho Lee, Jungwook Choi, Jun Won Choi

To ensure secure and dependable mobility in environments shared by humans and robots, social navigation robots should possess the capability to accurately perceive and predict the trajectories of nearby pedestrians. In this paper, we present a novel dataset of pedestrian trajectories, referred to as Social Interactive Trajectory (SiT) dataset, which can be used to train pedestrian detection, tracking, and trajectory prediction models needed to design social navigation robots. Our dataset includes sequential raw data captured by two 3D LiDARs and five cameras covering a 360-degree view, two inertial measurement unit (IMU) sensors, and real-time kinematic positioning (RTK), as well as annotations including 2D & 3D boxes, object classes, and object IDs. Thus far, various human trajectory datasets have been introduced to support the development of pedestrian motion forecasting models. Our SiT dataset differs from these datasets in the following two respects. First, whereas the pedestrian trajectory data in other datasets was obtained from static scenes, our data was collected while the robot navigates in a crowded environment, capturing human-robot interactive scenarios in motion. Second, our dataset has been carefully organized to facilitate training and evaluation of end-to-end prediction models encompassing 3D detection, 3D multi-object tracking, and trajectory prediction. This design allows for an end-to-end unified modular approach across different tasks. We have introduced a comprehensive benchmark for assessing models across all aforementioned tasks, and have showcased the performance of multiple baseline models as part of our evaluation. Our dataset provides a strong foundation for future research in pedestrian trajectory prediction, which could expedite the development of safe and agile social navigation robots. The SiT dataset, devkit, and pre-trained models are publicly released at: https://spalaboratory.github.io/SiT

Applications/Everything Else

Can (Sam) Chen, Christopher Beckham, Zixuan Liu, Xue (Steve) Liu, Chris Pal

We study offline model-based optimization to maximize a black-box objective function with a static dataset of designs and scores. These designs encompass a variety of domains, including materials, robots, DNA sequences, and proteins. A common approach trains a proxy on the static dataset and performs gradient ascent to obtain new designs. However, this often results in poor designs due to the proxy inaccuracies for out-of-distribution designs. Recent studies indicate that (a) gradient ascent with a mean ensemble of proxies generally outperforms simple gradient ascent, and (b) a trained proxy provides weak ranking supervision signals for design selection. Motivated by (a) and (b), we propose $\textit{parallel-mentoring}$ as an effective and novel method that facilitates mentoring among proxies, creating a more robust ensemble to mitigate the out-of-distribution issue. We focus on the three-proxy case in the main paper and our method consists of two modules. The first module, $\textit{voting-based pairwise supervision}$, operates on three parallel proxies and captures their ranking supervision signals as pairwise comparison labels. These labels are combined through majority voting to generate consensus labels, which incorporates ranking supervision signals from all proxies and enables mutual mentoring. Yet, label noise arises due to possible incorrect consensus. To alleviate this, we introduce an $\textit{adaptive soft-labeling}$ module with soft-labels initialized as consensus labels. Based on bi-level optimization, this module fine-tunes proxies in the inner level and learns more accurate labels in the outer level to adaptively mentor proxies, resulting in a more robust ensemble. Experiments validate the effectiveness of our method. Our code is available here.

Reinforcement Learning/Deep RL

Bo Liu, Yifeng Zhu, Chongkai Gao, Yihao Feng, Qiang Liu, Yuke Zhu, Peter Stone

Lifelong learning offers a promising paradigm of building a generalist agent that learns and adapts over its lifespan. Unlike traditional lifelong learning problems in image and text domains, which primarily involve the transfer of declarative knowledge of entities and concepts, lifelong learning in decision-making (LLDM) also necessitates the transfer of procedural knowledge, such as actions and behaviors. To advance research in LLDM, we introduce LIBERO, a novel benchmark of lifelong learning for robot manipulation. Specifically, LIBERO highlights five key research topics in LLDM: 1) how to efficiently transfer declarative knowledge, procedural knowledge, or the mixture of both; 2) how to design effective policy architectures and 3) effective algorithms for LLDM; 4) the robustness of a lifelong learner with respect to task ordering; and 5) the effect of model pretraining for LLDM. We develop an extendible procedural generation pipeline that can in principle generate infinitely many tasks. For benchmarking purpose, we create four task suites (130 tasks in total) that we use to investigate the above-mentioned research topics. To support sample-efficient learning, we provide high-quality human-teleoperated demonstration data for all tasks. Our extensive experiments present several insightful or even unexpected discoveries: sequential finetuning outperforms existing lifelong learning methods in forward transfer, no single visual encoder architecture excels at all types of knowledge transfer, and naive supervised pretraining can hinder agents' performance in the subsequent LLDM.

Applications/Computer Vision

QIANQIAN SHEN, Yunhan Zhao, Nahyun Kwon, Jeeeun Kim, Yanan Li, Shu Kong

Instance detection (InsDet) is a long-lasting problem in robotics and computer vision, aiming to detect object instances (predefined by some visual examples) in a cluttered scene. Despite its practical significance, its advancement is overshadowed by Object Detection, which aims to detect objects belonging to some predefined classes. One major reason is that current InsDet datasets are too small in scale by today's standards. For example, the popular InsDet dataset GMU (published in 2016) has only 23 instances, far less than COCO (80 classes), a well-known object detection dataset published in 2014. We are motivated to introduce a new InsDet dataset and protocol. First, we define a realistic setup for InsDet: training data consists of multi-view instance captures, along with diverse scene images allowing synthesizing training images by pasting instance images on them with free box annotations. Second, we release a real-world database, which contains multi-view capture of 100 object instances, and high-resolution (6k$\times$8k) testing images. Third, we extensively study baseline methods for InsDet on our dataset, analyze their performance and suggest future work. Somewhat surprisingly, using the off-the-shelf class-agnostic segmentation model (Segment Anything Model, SAM) and the self-supervised feature representation DINOv2 performs the best, achieving $>$10 AP better than end-to-end trained InsDet models that repurpose object detectors (e.g., FasterRCNN and RetinaNet).

Applications/Robotics

Nico Montali, John Lambert, Paul Mougin, Alex Kuefler, Nicholas Rhinehart, Michelle Li, Cole Gulino, Tristan Emrich, Zoey Yang, Shimon Whiteson 等

Simulation with realistic, interactive agents represents a key task for autonomous vehicle software development. In this work, we introduce the Waymo Open Sim Agents Challenge (WOSAC). WOSAC is the first public challenge to tackle this task and propose corresponding metrics. The goal of the challenge is to stimulate the design of realistic simulators that can be used to evaluate and train a behavior model for autonomous driving. We outline our evaluation methodology, present results for a number of different baseline simulation agent methods, and analyze several submissions to the 2023 competition which ran from March 16, 2023 to May 23, 2023. The WOSAC evaluation server remains open for submissions and we discuss open problems for the task.

Applications/Language, Speech and Dialog

Qiaozi Gao, Govind Thattai, Suhaila Shakiah, Xiaofeng Gao, Shreyas Pansare, Vasu Sharma, Gaurav Sukhatme, Hangjie Shi, Bofei Yang, Desheng Zhang 等

We introduce Alexa Arena, a user-centric simulation platform to facilitate research in building assistive conversational embodied agents. Alexa Arena features multi-room layouts and an abundance of interactable objects. With user-friendly graphics and control mechanisms, the platform supports the development of gamified robotic tasks readily accessible to general human users, allowing high-efficiency data collection and EAI system evaluation. Along with the platform, we introduce a dialog-enabled task completion benchmark with online human evaluations.

Applications/Robotics

Yangru Huang, Peixi Peng, Yifan Zhao, Haoran Xu, Mengyue Geng, Yonghong Tian

Integrating RGB frames with alternative modality inputs is gaining increasing traction in many vision-based reinforcement learning (RL) applications. Existing multi-modal vision-based RL methods usually follow a Global Value Estimation (GVE) pipeline, which uses a fused modality feature to obtain a unified global environmental description. However, such a feature-level fusion paradigm with a single critic may fall short in policy learning as it tends to overlook the distinct values of each modality. To remedy this, this paper proposes a Local modality-customized Value Estimation (LVE) paradigm, which dynamically estimates the contribution and adjusts the importance weight of each modality from a value-level perspective. Furthermore, a task-contextual re-fusion process is developed to achieve a task-level re-balance of estimations from both feature and value levels. To this end, a Hierarchical Adaptive Value Estimation (HAVE) framework is formed, which adaptively coordinates the contributions of individual modalities as well as their collective efficacy. Agents trained by HAVE are able to exploit the unique characteristics of various modalities while capturing their intricate interactions, achieving substantially improved performance. We specifically highlight the potency of our approach within the challenging landscape of autonomous driving, utilizing the CARLA benchmark with neuromorphic event and depth data to demonstrate HAVE's capability and the effectiveness of its distinct components.

Deep Learning/Generative Models and Autoencoders

Nic Fishman, Leo Klarner, Emile Mathieu, Michael Hutchinson, Valentin De Bortoli

Denoising diffusion models have recently emerged as the predominant paradigm for generative modelling on image domains. In addition, their extension to Riemannian manifolds has facilitated a range of applications across the natural sciences. While many of these problems stand to benefit from the ability to specify arbitrary, domain-informed constraints, this setting is not covered by the existing (Riemannian) diffusion model methodology. Recent work has attempted to address this issue by constructing novel noising processes based on the reflected Brownian motion and logarithmic barrier methods. However, the associated samplers are either computationally burdensome or only apply to convex subsets of Euclidean space. In this paper, we introduce an alternative, simple noising scheme based on Metropolis sampling that affords substantial gains in computational efficiency and empirical performance compared to the earlier samplers. Of independent interest, we prove that this new process corresponds to a valid discretisation of the reflected Brownian motion. We demonstrate the scalability and flexibility of our approach on a range of problem settings with convex and non-convex constraints, including applications from geospatial modelling, robotics and protein design.

Deep Learning/Other Representation Learning

Paul Pu Liang, Yun Cheng, Xiang Fan, Chun Kai Ling, Suzanne Nie, Richard Chen, Zihao Deng, Nicholas Allen, Randy Auerbach, Faisal Mahmood 等

The recent explosion of interest in multimodal applications has resulted in a wide selection of datasets and methods for representing and integrating information from different modalities. Despite these empirical advances, there remain fundamental research questions: How can we quantify the interactions that are necessary to solve a multimodal task? Subsequently, what are the most suitable multimodal models to capture these interactions? To answer these questions, we propose an information-theoretic approach to quantify the degree of redundancy, uniqueness, and synergy relating input modalities with an output task. We term these three measures as the PID statistics of a multimodal distribution (or PID for short), and introduce two new estimators for these PID statistics that scale to high-dimensional distributions. To validate PID estimation, we conduct extensive experiments on both synthetic datasets where the PID is known and on large-scale multimodal benchmarks where PID estimations are compared with human annotations. Finally, we demonstrate their usefulness in (1) quantifying interactions within multimodal datasets, (2) quantifying interactions captured by multimodal models, (3) principled approaches for model selection, and (4) three real-world case studies engaging with domain experts in pathology, mood prediction, and robotic perception where our framework helps to recommend strong multimodal models for each application.

Applications/Computer Vision

Meng Wei, Xiaoyu Yue, Wenwei Zhang, Shu Kong, Xihui Liu, Jiangmiao Pang

Segmenting and recognizing diverse object parts is a crucial ability in applications spanning various computer vision and robotic tasks. While significant progress has been made in object-level Open-Vocabulary Semantic Segmentation (OVSS), i.e., segmenting objects with arbitrary text, the corresponding part-level research poses additional challenges. Firstly, part segmentation inherently involves intricate boundaries, while limited annotated data compounds the challenge. Secondly, part segmentation introduces an open granularity challenge due to the diverse and often ambiguous definitions of parts in the open world. Furthermore, the large-scale vision and language models, which play a key role in the open vocabulary setting, struggle to recognize parts as effectively as objects. To comprehensively investigate and tackle these challenges, we propose an Open-Vocabulary Part Segmentation (OV-PARTS) benchmark. OV-PARTS includes refined versions of two publicly available datasets: Pascal-Part-116 and ADE20K-Part-234. And it covers three specific tasks: Generalized Zero-Shot Part Segmentation, Cross-Dataset Part Segmentation, and Few-Shot Part Segmentation, providing insights into analogical reasoning, open granularity and few-shot adapting abilities of models. Moreover, we analyze and adapt two prevailing paradigms of existing object-level OVSS methods for OV-PARTS. Extensive experimental analysis is conducted to inspire future research in leveraging foundational models for OV-PARTS. The code and dataset are available at https://github.com/kellyiss/OV_PARTS.

Reinforcement Learning/Batch Offline

Vladislav Kurenkov, Alexander Nikulin, Denis Tarasov, Sergey Kolesnikov

NetHack is known as the frontier of reinforcement learning research where learning-based methods still need to catch up to rule-based solutions. One of the promising directions for a breakthrough is using pre-collected datasets similar to recent developments in robotics, recommender systems, and more under the umbrella of offline reinforcement learning (ORL). Recently, a large-scale NetHack dataset was released; while it was a necessary step forward, it has yet to gain wide adoption in the ORL community. In this work, we argue that there are three major obstacles for adoption: tool-wise, implementation-wise, and benchmark-wise. To address them, we develop an open-source library that provides workflow fundamentals familiar to the ORL community: pre-defined D4RL-style tasks, uncluttered baseline implementations, and reliable evaluation tools with accompanying configs and logs synced to the cloud.

Applications/Robotics

Jiaming Ji, Borong Zhang, Jiayi Zhou, Xuehai Pan, Weidong Huang, Ruiyang Sun, Yiran Geng, Yifan Zhong, Josef Dai, Yaodong Yang

Artificial intelligence (AI) systems possess significant potential to drive societal progress. However, their deployment often faces obstacles due to substantial safety concerns. Safe reinforcement learning (SafeRL) emerges as a solution to optimize policies while simultaneously adhering to multiple constraints, thereby addressing the challenge of integrating reinforcement learning in safety-critical scenarios. In this paper, we present an environment suite called Safety-Gymnasium, which encompasses safety-critical tasks in both single and multi-agent scenarios, accepting vector and vision-only input. Additionally, we offer a library of algorithms named Safe Policy Optimization (SafePO), comprising 16 state-of-the-art SafeRL algorithms. This comprehensive library can serve as a validation tool for the research community. By introducing this benchmark, we aim to facilitate the evaluation and comparison of safety performance, thus fostering the development of reinforcement learning for safer, more reliable, and responsible real-world applications. The website of this project can be accessed at https://sites.google.com/view/safety-gymnasium.

Applications/Robotics

Vikash Kumar, Rutav Shah, Gaoyue Zhou, Vincent Moens, Vittorio Caggiano, Abhishek Gupta, Aravind Rajeswaran

We present RoboHive, a comprehensive software platform and ecosystem for research in the field of Robot Learning and Embodied Artificial Intelligence. Our platform encompasses a diverse range of pre-existing and novel environments, including dexterous manipulation with the Shadow Hand, whole-arm manipulation tasks with Franka and Fetch robots, quadruped locomotion, among others. Included environments are organized within and cover multiple domains such as hand manipulation, locomotion, multi-task, multi-agent, muscles, etc. In comparison to prior works, RoboHive offers a streamlined and unified task interface taking dependency on only a minimal set of well-maintained packages, features tasks with high physics fidelity and rich visual diversity, and supports common hardware drivers for real-world deployment. The unified interface of RoboHive offers a convenient and accessible abstraction for algorithmic research in imitation, reinforcement, multi-task, and hierarchical learning. Furthermore, RoboHive includes expert demonstrations and baseline results for most environments, providing a standard for benchmarking and comparisons. Details: https://sites.google.com/view/robohive

Deep Learning/Generative Models and Autoencoders

Eric Zelikman, Qian Huang, Gabriel Poesia, Noah Goodman, Nick Haber

Despite recent success in large language model (LLM) reasoning, LLMs struggle with hierarchical multi-step reasoning tasks like generating complex programs. For these tasks, humans often start with a high-level algorithmic design and implement each part gradually. We introduce Parsel, a framework enabling automatic implementation and validation of complex algorithms with code LLMs. With Parsel, we automatically decompose algorithmic tasks into hierarchical natural language function descriptions and then search over combinations of possible function implementations using tests. We show that Parsel can be used across domains requiring hierarchical reasoning, including program synthesis and robotic planning. We find that, using Parsel, LLMs solve more competition-level problems in the APPS dataset, resulting in pass rates over 75\% higher than prior results from directly sampling AlphaCode and Codex, while often using a smaller sample budget. Moreover, with automatically generated tests, we find that Parsel can improve the state-of-the-art pass@1 performance on HumanEval from 67\% to 85\%. We also find that LLM-generated robotic plans using Parsel are more than twice as likely to be considered accurate than directly generated plans. Lastly, we explore how Parsel addresses LLM limitations and discuss how Parsel may be useful for human programmers. We release our code at https://github.com/ezelikman/parsel.

Applications/Computer Vision

Hao Zheng, Regina Lee, Yuqian Lu

Understanding comprehensive assembly knowledge from videos is critical for futuristic ultra-intelligent industry. To enable technological breakthrough, we present HA-ViD – the first human assembly video dataset that features representative industrial assembly scenarios, natural procedural knowledge acquisition process, and consistent human-robot shared annotations. Specifically, HA-ViD captures diverse collaboration patterns of real-world assembly, natural human behaviors and learning progression during assembly, and granulate action annotations to subject, action verb, manipulated object, target object, and tool. We provide 3222 multi-view and multi-modality videos), 1.5M frames, 96K temporal labels and 2M spatial labels. We benchmark four foundational video understanding tasks: action recognition, action segmentation, object detection and multi-object tracking. Importantly, we analyze their performance and the further reasoning steps for comprehending knowledge in assembly progress, process efficiency, task collaboration, skill parameters and human intention. Details of HA-ViD is available at: https://iai-hrc.github.io/ha-vid.