Grounding language to the visual observations of a navigating agent can be performed using off-the-shelf visual-language models pretrained on Internet-scale data (e.g., image captions). While this is useful for matching images to natural language descriptions of object goals, it remains disjoint from the process of mapping the environment, so that it lacks the spatial precision of classic geometric maps. To address this problem, we propose VLMaps, a spatial map representation that directly fuses pretrained visual-language features with a 3D reconstruction of the physical world. VLMaps can be autonomously built from video feed on robots using standard exploration approaches and enables natural language indexing of the map without additional labeled data. Specifically, when combined with large language models (LLMs), VLMaps can be used to (i) translate natural language commands into a sequence of open-vocabulary navigation goals (which, beyond prior work, can be spatial by construction, e.g., "in between the sofa and TV" or "three meters to the right of the chair") directly localized in the map, and (ii) can be shared among multiple robots with different embodiments to generate new obstacle maps on-the-fly (by using a list of obstacle categories). Extensive experiments carried out in simulated and real world environments show that VLMaps enable navigation according to more complex language instructions than existing methods. Videos are available at //vlmaps.github.io.
相關內容
We present the Interactive Task Encoding System (ITES) for teaching robots to perform manipulative tasks. ITES is designed as an input system for the Learning-from-Observation (LfO) framework, which enables household robots to be programmed using few-shot human demonstrations without the need for coding. In contrast to previous LfO systems that rely solely on visual demonstrations, ITES leverages both verbal instructions and interaction to enhance recognition robustness, thus enabling multimodal LfO. ITES identifies tasks from verbal instructions and extracts parameters from visual demonstrations. Meanwhile, the recognition result was reviewed by the user for interactive correction. Evaluations conducted on a real robot demonstrate the successful teaching of multiple operations for several scenarios, suggesting the usefulness of ITES for multimodal LfO. The source code is available at //github.com/microsoft/symbolic-robot-teaching-interface.
To make progress towards multi-modal AI assistants which can guide users to achieve complex multi-step goals, we propose the task of Visual Planning for Assistance (VPA). Given a goal briefly described in natural language, e.g., "make a shelf", and a video of the user's progress so far, the aim of VPA is to obtain a plan, i.e., a sequence of actions such as "sand shelf", "paint shelf", etc., to achieve the goal. This requires assessing the user's progress from the untrimmed video, and relating it to the requirements of underlying goal, i.e., relevance of actions and ordering dependencies amongst them. Consequently, this requires handling long video history, and arbitrarily complex action dependencies. To address these challenges, we decompose VPA into video action segmentation and forecasting. We formulate the forecasting step as a multi-modal sequence modeling problem and present Visual Language Model based Planner (VLaMP), which leverages pre-trained LMs as the sequence model. We demonstrate that VLaMP performs significantly better than baselines w.r.t all metrics that evaluate the generated plan. Moreover, through extensive ablations, we also isolate the value of language pre-training, visual observations, and goal information on the performance. We will release our data, model, and code to enable future research on visual planning for assistance.
Language is essentially a complex, intricate system of human expressions governed by grammatical rules. It poses a significant challenge to develop capable AI algorithms for comprehending and grasping a language. As a major approach, language modeling has been widely studied for language understanding and generation in the past two decades, evolving from statistical language models to neural language models. Recently, pre-trained language models (PLMs) have been proposed by pre-training Transformer models over large-scale corpora, showing strong capabilities in solving various NLP tasks. Since researchers have found that model scaling can lead to performance improvement, they further study the scaling effect by increasing the model size to an even larger size. Interestingly, when the parameter scale exceeds a certain level, these enlarged language models not only achieve a significant performance improvement but also show some special abilities that are not present in small-scale language models. To discriminate the difference in parameter scale, the research community has coined the term large language models (LLM) for the PLMs of significant size. Recently, the research on LLMs has been largely advanced by both academia and industry, and a remarkable progress is the launch of ChatGPT, which has attracted widespread attention from society. The technical evolution of LLMs has been making an important impact on the entire AI community, which would revolutionize the way how we develop and use AI algorithms. In this survey, we review the recent advances of LLMs by introducing the background, key findings, and mainstream techniques. In particular, we focus on four major aspects of LLMs, namely pre-training, adaptation tuning, utilization, and capacity evaluation. Besides, we also summarize the available resources for developing LLMs and discuss the remaining issues for future directions.
In applications that involve human-robot interaction (HRI), human-robot teaming (HRT), and cooperative human-machine systems, the inference of the human partner's intent is of critical importance. This paper presents a method for the inference of the human operator's navigational intent, in the context of mobile robots that provide full or partial (e.g., shared control) teleoperation. We propose the Machine Learning Operator Intent Inference (MLOII) method, which a) processes spatial data collected by the robot's sensors; b) utilizes a supervised machine learning algorithm to estimate the operator's most probable navigational goal online. The proposed method's ability to reliably and efficiently infer the intent of the human operator is experimentally evaluated in realistically simulated exploration and remote inspection scenarios. The results in terms of accuracy and uncertainty indicate that the proposed method is comparable to another state-of-the-art method found in the literature.
Training segmentation models for medical images continues to be challenging due to the limited availability and acquisition expense of data annotations. Segment Anything Model (SAM) is a foundation model trained on over 1 billion annotations, predominantly for natural images, that is intended to be able to segment the user-defined object of interest in an interactive manner. Despite its impressive performance on natural images, it is unclear how the model is affected when shifting to medical image domains. Here, we perform an extensive evaluation of SAM's ability to segment medical images on a collection of 11 medical imaging datasets from various modalities and anatomies. In our experiments, we generated point prompts using a standard method that simulates interactive segmentation. Experimental results show that SAM's performance based on single prompts highly varies depending on the task and the dataset, i.e., from 0.1135 for a spine MRI dataset to 0.8650 for a hip x-ray dataset, evaluated by IoU. Performance appears to be high for tasks including well-circumscribed objects with unambiguous prompts and poorer in many other scenarios such as segmentation of tumors. When multiple prompts are provided, performance improves only slightly overall, but more so for datasets where the object is not contiguous. An additional comparison to RITM showed a much better performance of SAM for one prompt but a similar performance of the two methods for a larger number of prompts. We conclude that SAM shows impressive performance for some datasets given the zero-shot learning setup but poor to moderate performance for multiple other datasets. While SAM as a model and as a learning paradigm might be impactful in the medical imaging domain, extensive research is needed to identify the proper ways of adapting it in this domain.
Multimodal learning helps to comprehensively understand the world, by integrating different senses. Accordingly, multiple input modalities are expected to boost model performance, but we actually find that they are not fully exploited even when the multimodal model outperforms its uni-modal counterpart. Specifically, in this paper we point out that existing multimodal discriminative models, in which uniform objective is designed for all modalities, could remain under-optimized uni-modal representations, caused by another dominated modality in some scenarios, e.g., sound in blowing wind event, vision in drawing picture event, etc. To alleviate this optimization imbalance, we propose on-the-fly gradient modulation to adaptively control the optimization of each modality, via monitoring the discrepancy of their contribution towards the learning objective. Further, an extra Gaussian noise that changes dynamically is introduced to avoid possible generalization drop caused by gradient modulation. As a result, we achieve considerable improvement over common fusion methods on different multimodal tasks, and this simple strategy can also boost existing multimodal methods, which illustrates its efficacy and versatility. The source code is available at \url{//github.com/GeWu-Lab/OGM-GE_CVPR2022}.
Medical Visual Question Answering (VQA) is a combination of medical artificial intelligence and popular VQA challenges. Given a medical image and a clinically relevant question in natural language, the medical VQA system is expected to predict a plausible and convincing answer. Although the general-domain VQA has been extensively studied, the medical VQA still needs specific investigation and exploration due to its task features. In the first part of this survey, we cover and discuss the publicly available medical VQA datasets up to date about the data source, data quantity, and task feature. In the second part, we review the approaches used in medical VQA tasks. In the last part, we analyze some medical-specific challenges for the field and discuss future research directions.
Effective multi-robot teams require the ability to move to goals in complex environments in order to address real-world applications such as search and rescue. Multi-robot teams should be able to operate in a completely decentralized manner, with individual robot team members being capable of acting without explicit communication between neighbors. In this paper, we propose a novel game theoretic model that enables decentralized and communication-free navigation to a goal position. Robots each play their own distributed game by estimating the behavior of their local teammates in order to identify behaviors that move them in the direction of the goal, while also avoiding obstacles and maintaining team cohesion without collisions. We prove theoretically that generated actions approach a Nash equilibrium, which also corresponds to an optimal strategy identified for each robot. We show through extensive simulations that our approach enables decentralized and communication-free navigation by a multi-robot system to a goal position, and is able to avoid obstacles and collisions, maintain connectivity, and respond robustly to sensor noise.
Breakthroughs in machine learning in the last decade have led to `digital intelligence', i.e. machine learning models capable of learning from vast amounts of labeled data to perform several digital tasks such as speech recognition, face recognition, machine translation and so on. The goal of this thesis is to make progress towards designing algorithms capable of `physical intelligence', i.e. building intelligent autonomous navigation agents capable of learning to perform complex navigation tasks in the physical world involving visual perception, natural language understanding, reasoning, planning, and sequential decision making. Despite several advances in classical navigation methods in the last few decades, current navigation agents struggle at long-term semantic navigation tasks. In the first part of the thesis, we discuss our work on short-term navigation using end-to-end reinforcement learning to tackle challenges such as obstacle avoidance, semantic perception, language grounding, and reasoning. In the second part, we present a new class of navigation methods based on modular learning and structured explicit map representations, which leverage the strengths of both classical and end-to-end learning methods, to tackle long-term navigation tasks. We show that these methods are able to effectively tackle challenges such as localization, mapping, long-term planning, exploration and learning semantic priors. These modular learning methods are capable of long-term spatial and semantic understanding and achieve state-of-the-art results on various navigation tasks.
We study joint learning of Convolutional Neural Network (CNN) and Transformer for vision-language pre-training (VLPT) which aims to learn cross-modal alignments from millions of image-text pairs. State-of-the-art approaches extract salient image regions and align regions with words step-by-step. As region-based visual features usually represent parts of an image, it is challenging for existing vision-language models to fully understand the semantics from paired natural languages. In this paper, we propose SOHO to "See Out of tHe bOx" that takes a whole image as input, and learns vision-language representation in an end-to-end manner. SOHO does not require bounding box annotations which enables inference 10 times faster than region-based approaches. In particular, SOHO learns to extract comprehensive yet compact image features through a visual dictionary (VD) that facilitates cross-modal understanding. VD is designed to represent consistent visual abstractions of similar semantics. It is updated on-the-fly and utilized in our proposed pre-training task Masked Visual Modeling (MVM). We conduct experiments on four well-established vision-language tasks by following standard VLPT settings. In particular, SOHO achieves absolute gains of 2.0% R@1 score on MSCOCO text retrieval 5k test split, 1.5% accuracy on NLVR$^2$ test-P split, 6.7% accuracy on SNLI-VE test split, respectively.
小貼士
登錄享
相關主題
注冊地址： 北京市海淀區羊坊店路18號2幢3層301-191