Reinforcement learning (RL), imitation learning (IL), and task and motion planning (TAMP) have demonstrated impressive performance across various robotic manipulation tasks. However, these approaches have been limited to learning simple behaviors in current real-world manipulation benchmarks, such as pushing or pick-and-place. To enable more complex, long-horizon behaviors of an autonomous robot, we propose to focus on real-world furniture assembly, a complex, long-horizon robot manipulation task that requires addressing many current robotic manipulation challenges to solve. We present FurnitureBench, a reproducible real-world furniture assembly benchmark aimed at providing a low barrier for entry and being easily reproducible, so that researchers across the world can reliably test their algorithms and compare them against prior work. For ease of use, we provide 200+ hours of pre-collected data (5000+ demonstrations), 3D printable furniture models, a robotic environment setup guide, and systematic task initialization. Furthermore, we provide FurnitureSim, a fast and realistic simulator of FurnitureBench. We benchmark the performance of offline RL and IL algorithms on our assembly tasks and demonstrate the need to improve such algorithms to be able to solve our tasks in the real world, providing ample opportunities for future research.
相關內容
Solving long sequential tasks poses a significant challenge in embodied artificial intelligence. Enabling a robotic system to perform diverse sequential tasks with a broad range of manipulation skills is an active area of research. In this work, we present a Hybrid Hierarchical Learning framework, the Robotic Manipulation Network (ROMAN), to address the challenge of solving multiple complex tasks over long time horizons in robotic manipulation. ROMAN achieves task versatility and robust failure recovery by integrating behavioural cloning, imitation learning, and reinforcement learning. It consists of a central manipulation network that coordinates an ensemble of various neural networks, each specialising in distinct re-combinable sub-tasks to generate their correct in-sequence actions for solving complex long-horizon manipulation tasks. Experimental results show that by orchestrating and activating these specialised manipulation experts, ROMAN generates correct sequential activations for accomplishing long sequences of sophisticated manipulation tasks and achieving adaptive behaviours beyond demonstrations, while exhibiting robustness to various sensory noises. These results demonstrate the significance and versatility of ROMAN's dynamic adaptability featuring autonomous failure recovery capabilities, and highlight its potential for various autonomous manipulation tasks that demand adaptive motor skills.
Autonomous racing is a research field gaining large popularity, as it pushes autonomous driving algorithms to their limits and serves as a catalyst for general autonomous driving. For scaled autonomous racing platforms, the computational constraint and complexity often limit the use of Model Predictive Control (MPC). As a consequence, geometric controllers are the most frequently deployed controllers. They prove to be performant while yielding implementation and operational simplicity. Yet, they inherently lack the incorporation of model dynamics, thus limiting the race car to a velocity domain where tire slip can be neglected. This paper presents Model- and Acceleration-based Pursuit (MAP) a high-performance model-based trajectory tracking algorithm that preserves the simplicity of geometric approaches while leveraging tire dynamics. The proposed algorithm allows accurate tracking of a trajectory at unprecedented velocities compared to State-of-the-Art (SotA) geometric controllers. The MAP controller is experimentally validated and outperforms the reference geometric controller four-fold in terms of lateral tracking error, yielding a tracking error of 0.055m at tested speeds up to 11m/s.
Large language models (LLMs) are gaining increasing popularity in both academia and industry, owing to their unprecedented performance in various applications. As LLMs continue to play a vital role in both research and daily use, their evaluation becomes increasingly critical, not only at the task level, but also at the society level for better understanding of their potential risks. Over the past years, significant efforts have been made to examine LLMs from various perspectives. This paper presents a comprehensive review of these evaluation methods for LLMs, focusing on three key dimensions: what to evaluate, where to evaluate, and how to evaluate. Firstly, we provide an overview from the perspective of evaluation tasks, encompassing general natural language processing tasks, reasoning, medical usage, ethics, educations, natural and social sciences, agent applications, and other areas. Secondly, we answer the `where' and `how' questions by diving into the evaluation methods and benchmarks, which serve as crucial components in assessing performance of LLMs. Then, we summarize the success and failure cases of LLMs in different tasks. Finally, we shed light on several future challenges that lie ahead in LLMs evaluation. Our aim is to offer invaluable insights to researchers in the realm of LLMs evaluation, thereby aiding the development of more proficient LLMs. Our key point is that evaluation should be treated as an essential discipline to better assist the development of LLMs. We consistently maintain the related open-source materials at: //github.com/MLGroupJLU/LLM-eval-survey.
As large language models (LLMs) continue to advance, accurately and comprehensively evaluating their performance becomes increasingly challenging. Conventionally, human evaluations are considered the gold standard in natural language generation. Recent advancements incorporate state-of-the-art LLMs as proxies for human judges in evaluation processes. Nonetheless, the extent to which humans and LLMs are capable evaluators remains uncertain. This study aims to investigate the behavior of both crowd-sourced human and LLM-based judges when comparing outputs from different models. To accomplish this, we curate a dataset comprising intentionally flawed machine-generated answers. Our findings indicate that despite the potentially greater danger posed by factual errors, answers with factual errors were still rated more favorably compared to answers that were too short or contained grammatical errors. This highlights a concerning bias in the evaluation process. To address this issue, we propose to independently evaluate machine-generated text across multiple dimensions, rather than merging all the evaluation aspects into a single score. We instantiate this idea with the Elo rating system, resulting in the Multi-Elo Rating System. Empirical results from our study reveal that this proposed approach significantly enhances the quality of LLM-based evaluations, particularly in terms of factual accuracy. However, notable improvement is not observed in crowd-sourced-based evaluations, suggesting the need for further investigation and refinement.
Automatic Robotic Assembly Sequence Planning (RASP) can significantly improve productivity and resilience in modern manufacturing along with the growing need for greater product customization. One of the main challenges in realizing such automation resides in efficiently finding solutions from a growing number of potential sequences for increasingly complex assemblies. Besides, costly feasibility checks are always required for the robotic system. To address this, we propose a holistic graphical approach including a graph representation called Assembly Graph for product assemblies and a policy architecture, Graph Assembly Processing Network, dubbed GRACE for assembly sequence generation. Secondly, we use GRACE to extract meaningful information from the graph input and predict assembly sequences in a step-by-step manner. In experiments, we show that our approach can predict feasible assembly sequences across product variants of aluminum profiles based on data collected in simulation of a dual-armed robotic system. We further demonstrate that our method is capable of detecting infeasible assemblies, substantially alleviating the undesirable impacts from false predictions, and hence facilitating real-world deployment soon. Code and training data are available at //github.com/DLR-RM/GRACE.
This paper investigates the intelligent computing task-oriented computing offloading and semantic compression in mobile edge computing (MEC) systems. With the popularity of intelligent applications in various industries, terminals increasingly need to offload intelligent computing tasks with complex demands to MEC servers for computing, which is a great challenge for bandwidth and computing capacity allocation in MEC systems. Considering the accuracy requirement of intelligent computing tasks, we formulate an optimization problem of computing offloading and semantic compression. We jointly optimize the system utility which are represented as computing accuracy and task delay respectively to acquire the optimized system utility. To solve the proposed optimization problem, we decompose it into computing capacity allocation subproblem and compression offloading subproblem and obtain solutions through convex optimization and successive convex approximation. After that, the offloading decisions, computing capacity and compressed ratio are obtained in closed forms. We design the computing offloading and semantic compression algorithm for intelligent computing tasks in MEC systems then. Simulation results represent that our algorithm converges quickly and acquires better performance and resource utilization efficiency through the trend with total number of users and computing capacity compared with benchmarks.
Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable artifacts, especially in practical scenarios. Previous works typically suppress artifacts with an extra loss penalty in the training phase. They only work for in-distribution artifact types generated during training. When applied in real-world scenarios, we observe that those improved methods still generate obviously annoying artifacts during inference. In this paper, we analyze the cause and characteristics of the GAN artifacts produced in unseen test data without ground-truths. We then develop a novel method, namely, DeSRA, to Detect and then Delete those SR Artifacts in practice. Specifically, we propose to measure a relative local variance distance from MSE-SR results and GAN-SR results, and locate the problematic areas based on the above distance and semantic-aware thresholds. After detecting the artifact regions, we develop a finetune procedure to improve GAN-based SR models with a few samples, so that they can deal with similar types of artifacts in more unseen real data. Equipped with our DeSRA, we can successfully eliminate artifacts from inference and improve the ability of SR models to be applied in real-world scenarios. The code will be available at //github.com/TencentARC/DeSRA.
The development of large language models (LLMs) such as ChatGPT has brought a lot of attention recently. However, their evaluation in the benchmark academic datasets remains under-explored due to the difficulty of evaluating the generative outputs produced by this model against the ground truth. In this paper, we aim to present a thorough evaluation of ChatGPT's performance on diverse academic datasets, covering tasks like question-answering, text summarization, code generation, commonsense reasoning, mathematical problem-solving, machine translation, bias detection, and ethical considerations. Specifically, we evaluate ChatGPT across 140 tasks and analyze 255K responses it generates in these datasets. This makes our work the largest evaluation of ChatGPT in NLP benchmarks. In short, our study aims to validate the strengths and weaknesses of ChatGPT in various tasks and provide insights for future research using LLMs. We also report a new emergent ability to follow multi-query instructions that we mostly found in ChatGPT and other instruction-tuned models. Our extensive evaluation shows that even though ChatGPT is capable of performing a wide variety of tasks, and may obtain impressive performance in several benchmark datasets, it is still far from achieving the ability to reliably solve many challenging tasks. By providing a thorough assessment of ChatGPT's performance across diverse NLP tasks, this paper sets the stage for a targeted deployment of ChatGPT-like LLMs in real-world applications.
Vertical Federated Learning (VFL) is a crucial paradigm for training machine learning models on feature-partitioned, distributed data. However, due to privacy restrictions, few public real-world VFL datasets exist for algorithm evaluation, and these represent a limited array of feature distributions. Existing benchmarks often resort to synthetic datasets, derived from arbitrary feature splits from a global set, which only capture a subset of feature distributions, leading to inadequate algorithm performance assessment. This paper addresses these shortcomings by introducing two key factors affecting VFL performance - feature importance and feature correlation - and proposing associated evaluation metrics and dataset splitting methods. Additionally, we introduce a real VFL dataset to address the deficit in image-image VFL scenarios. Our comprehensive evaluation of cutting-edge VFL algorithms provides valuable insights for future research in the field.
Meta-reinforcement learning algorithms can enable robots to acquire new skills much more quickly, by leveraging prior experience to learn how to learn. However, much of the current research on meta-reinforcement learning focuses on task distributions that are very narrow. For example, a commonly used meta-reinforcement learning benchmark uses different running velocities for a simulated robot as different tasks. When policies are meta-trained on such narrow task distributions, they cannot possibly generalize to more quickly acquire entirely new tasks. Therefore, if the aim of these methods is to enable faster acquisition of entirely new behaviors, we must evaluate them on task distributions that are sufficiently broad to enable generalization to new behaviors. In this paper, we propose an open-source simulated benchmark for meta-reinforcement learning and multi-task learning consisting of 50 distinct robotic manipulation tasks. Our aim is to make it possible to develop algorithms that generalize to accelerate the acquisition of entirely new, held-out tasks. We evaluate 6 state-of-the-art meta-reinforcement learning and multi-task learning algorithms on these tasks. Surprisingly, while each task and its variations (e.g., with different object positions) can be learned with reasonable success, these algorithms struggle to learn with multiple tasks at the same time, even with as few as ten distinct training tasks. Our analysis and open-source environments pave the way for future research in multi-task learning and meta-learning that can enable meaningful generalization, thereby unlocking the full potential of these methods.
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191