ترغب بنشر مسار تعليمي؟ اضغط هنا

Visual-and-Language Navigation: A Survey and Taxonomy

82   0   0.0 ( 0 )
 نشر من قبل Wansen Wu
 تاريخ النشر 2021
  مجال البحث الهندسة المعلوماتية
والبحث باللغة English




اسأل ChatGPT حول البحث

An agent that can understand natural-language instruction and carry out corresponding actions in the visual world is one of the long-term challenges of Artificial Intelligent (AI). Due to multifarious instructions from humans, it requires the agent can link natural language to vision and action in unstructured, previously unseen environments. If the instruction given by human is a navigation task, this challenge is called Visual-and-Language Navigation (VLN). It is a booming multi-disciplinary field of increasing importance and with extraordinary practicality. Instead of focusing on the details of specific methods, this paper provides a comprehensive survey on VLN tasks and makes a classification carefully according the different characteristics of language instructions in these tasks. According to when the instructions are given, the tasks can be divided into single-turn and multi-turn. For single-turn tasks, we further divided them into goal-orientation and route-orientation based on whether the instructions contain a route. For multi-turn tasks, we divided them into imperative task and interactive task based on whether the agent responses to the instructions. This taxonomy enable researchers to better grasp the key point of a specific task and identify directions for future research.

قيم البحث

اقرأ أيضاً

Vision-language navigation (VLN) is the task of entailing an agent to carry out navigational instructions inside photo-realistic environments. One of the key challenges in VLN is how to conduct a robust navigation by mitigating the uncertainty caused by ambiguous instructions and insufficient observation of the environment. Agents trained by current approaches typically suffer from this and would consequently struggle to avoid random and inefficient actions at every step. In contrast, when humans face such a challenge, they can still maintain robust navigation by actively exploring the surroundings to gather more information and thus make more confident navigation decisions. This work draws inspiration from human navigation behavior and endows an agent with an active information gathering ability for a more intelligent vision-language navigation policy. To achieve this, we propose an end-to-end framework for learning an exploration policy that decides i) when and where to explore, ii) what information is worth gathering during exploration, and iii) how to adjust the navigation decision after the exploration. The experimental results show promising exploration strategies emerged from training, which leads to significant boost in navigation performance. On the R2R challenge leaderboard, our agent gets promising results all three VLN settings, i.e., single run, pre-exploration, and beam search.
Most Visual Question Answering (VQA) models suffer from the language prior problem, which is caused by inherent data biases. Specifically, VQA models tend to answer questions (e.g., what color is the banana?) based on the high-frequency answers (e.g. , yellow) ignoring image contents. Existing approaches tackle this problem by creating delicate models or introducing additional visual annotations to reduce question dependency while strengthening image dependency. However, they are still subject to the language prior problem since the data biases have not been even alleviated. In this paper, we introduce a self-supervised learning framework to solve this problem. Concretely, we first automatically generate labeled data to balance the biased data, and propose a self-supervised auxiliary task to utilize the balanced data to assist the base VQA model to overcome language priors. Our method can compensate for the data biases by generating balanced data without introducing external annotations. Experimental results show that our method can significantly outperform the state-of-the-art, improving the overall accuracy from 49.50% to 57.59% on the most commonly used benchmark VQA-CP v2. In other words, we can increase the performance of annotation-based methods by 16% without using external annotations.
Visual navigation and three-dimensional (3D) scene reconstruction are essential for robotics to interact with the surrounding environment. Large-scale scenes and critical camera motions are great challenges facing the research community to achieve th is goal. We raised a pose-only imaging geometry framework and algorithms that can help solve these challenges. The representation is a linear function of camera global translations, which allows for efficient and robust camera motion estimation. As a result, the spatial feature coordinates can be analytically reconstructed and do not require nonlinear optimization. Experiments demonstrate that the computational efficiency of recovering the scene and associated camera poses is significantly improved by 2-4 orders of magnitude. This solution might be promising to unlock real-time 3D visual computing in many forefront applications.
As a fundamental problem for Artificial Intelligence, multi-agent system (MAS) is making rapid progress, mainly driven by multi-agent reinforcement learning (MARL) techniques. However, previous MARL methods largely focused on grid-world like or game environments; MAS in visually rich environments has remained less explored. To narrow this gap and emphasize the crucial role of perception in MAS, we propose a large-scale 3D dataset, CollaVN, for multi-agent visual navigation (MAVN). In CollaVN, multiple agents are entailed to cooperatively navigate across photo-realistic environments to reach target locations. Diverse MAVN variants are explored to make our problem more general. Moreover, a memory-augmented communication framework is proposed. Each agent is equipped with a private, external memory to persistently store communication information. This allows agents to make better use of their past communication information, enabling more efficient collaboration and robust long-term planning. In our experiments, several baselines and evaluation metrics are designed. We also empirically verify the efficacy of our proposed MARL approach across different MAVN task settings.
Interaction and navigation defined by natural language instructions in dynamic environments pose significant challenges for neural agents. This paper focuses on addressing two challenges: handling long sequence of subtasks, and understanding complex human instructions. We propose Episodic Transformer (E.T.), a multimodal transformer that encodes language inputs and the full episode history of visual observations and actions. To improve training, we leverage synthetic instructions as an intermediate representation that decouples understanding the visual appearance of an environment from the variations of natural language instructions. We demonstrate that encoding the history with a transformer is critical to solve compositional tasks, and that pretraining and joint training with synthetic instructions further improve the performance. Our approach sets a new state of the art on the challenging ALFRED benchmark, achieving 38.4% and 8.5% task success rates on seen and unseen test splits.

الأسئلة المقترحة

التعليقات
جاري جلب التعليقات جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
mircosoft-partner

هل ترغب بارسال اشعارات عن اخر التحديثات في شمرا-اكاديميا