Towards Learning a Generalist Model for Embodied Navigation

• URL: http://arxiv.org/abs/2312.02010v3
• Date: Mon, 1 Apr 2024 07:21:52 GMT
• Title: Towards Learning a Generalist Model for Embodied Navigation
• Authors: Duo Zheng, Shijia Huang, Lin Zhao, Yiwu Zhong, Liwei Wang,
• Abstract summary: We propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. We conduct extensive experiments to evaluate the performance and generalizability of our model.
• Score: 24.816490551945435
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Building a generalist agent that can interact with the world is the intriguing target of AI systems, thus spurring the research for embodied navigation, where an agent is required to navigate according to instructions or respond to queries. Despite the major progress attained, previous works primarily focus on task-specific agents and lack generalizability to unseen scenarios. Recently, LLMs have presented remarkable capabilities across various fields, and provided a promising opportunity for embodied navigation. Drawing on this, we propose the first generalist model for embodied navigation, NaviLLM. It adapts LLMs to embodied navigation by introducing schema-based instruction. The schema-based instruction flexibly casts various tasks into generation problems, thereby unifying a wide range of tasks. This approach allows us to integrate diverse data sources from various datasets into the training, equipping NaviLLM with a wide range of capabilities required by embodied navigation. We conduct extensive experiments to evaluate the performance and generalizability of our model. The experimental results demonstrate that our unified model achieves state-of-the-art performance on CVDN, SOON, and ScanQA. Specifically, it surpasses the previous stats-of-the-art method by a significant margin of 29% in goal progress on CVDN. Moreover, our model also demonstrates strong generalizability and presents impressive results on unseen tasks, e.g., embodied question answering and 3D captioning.

Related papers

• Scaling Data Generation in Vision-and-Language Navigation [116.95534559103788]
  We propose an effective paradigm for generating large-scale data for learning. We apply 1200+ photo-realistic environments from HM3D and Gibson datasets and synthesizes 4.9 million instruction trajectory pairs. Thanks to our large-scale dataset, the performance of an existing agent can be pushed up (+11% absolute with regard to previous SoTA) to a significantly new best of 80% single-run success rate on the R2R test split by simple imitation learning.
  arXiv  Detail & Related papers  (2023-07-28T16:03:28Z)
• NavGPT: Explicit Reasoning in Vision-and-Language Navigation with Large Language Models [17.495162643127003]
  We introduce the NavGPT to reveal the reasoning capability of GPT models in complex embodied scenes. NavGPT takes the textual descriptions of visual observations, navigation history, and future explorable directions as inputs to reason the agent's current status. We show that NavGPT is capable of generating high-quality navigational instructions from observations and actions along a path.
  arXiv  Detail & Related papers  (2023-05-26T14:41:06Z)
• Masked Path Modeling for Vision-and-Language Navigation [41.7517631477082]
  Vision-and-language navigation (VLN) agents are trained to navigate in real-world environments by following natural language instructions. Previous approaches have attempted to address this issue by introducing additional supervision during training. We introduce a masked path modeling (MPM) objective, which pretrains an agent using self-collected data for downstream navigation tasks.
  arXiv  Detail & Related papers  (2023-05-23T17:20:20Z)
• ENTL: Embodied Navigation Trajectory Learner [37.43079415330256]
  We propose a method for extracting long sequence representations for embodied navigation. We train our model using vector-quantized predictions of future states conditioned on current actions. A key property of our approach is that the model is pre-trained without any explicit reward signal.
  arXiv  Detail & Related papers  (2023-04-05T17:58:33Z)
• Towards Versatile Embodied Navigation [120.73460380993305]
  Vienna is a versatile embodied navigation agent that simultaneously learns to perform the four navigation tasks with one model. We empirically demonstrate that, compared with learning each visual navigation task individually, our agent achieves comparable or even better performance with reduced complexity.
  arXiv  Detail & Related papers  (2022-10-30T11:53:49Z)
• Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation [97.17517060585875]
  We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks. Our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.
  arXiv  Detail & Related papers  (2022-02-05T00:07:21Z)
• Curriculum Learning for Vision-and-Language Navigation [16.695511663714214]
  Vision-and-Language Navigation (VLN) is a task where an agent navigates in an embodied indoor environment under human instructions. Previous works ignore the distribution of sample difficulty and we argue that this potentially degrade their agent performance. We propose a novel curriculum-based training paradigm for VLN tasks that can balance human prior knowledge and agent learning progress.
  arXiv  Detail & Related papers  (2021-11-14T03:02:07Z)
• Hierarchical Few-Shot Imitation with Skill Transition Models [66.81252581083199]
  Few-shot Imitation with Skill Transition Models (FIST) is an algorithm that extracts skills from offline data and utilizes them to generalize to unseen tasks. We show that FIST is capable of generalizing to new tasks and substantially outperforms prior baselines in navigation experiments.
  arXiv  Detail & Related papers  (2021-07-19T15:56:01Z)
• Soft Expert Reward Learning for Vision-and-Language Navigation [94.86954695912125]
  Vision-and-Language Navigation (VLN) requires an agent to find a specified spot in an unseen environment by following natural language instructions. We introduce a Soft Expert Reward Learning (SERL) model to overcome the reward engineering designing and generalisation problems of the VLN task.
  arXiv  Detail & Related papers  (2020-07-21T14:17:36Z)
• Improving Target-driven Visual Navigation with Attention on 3D Spatial Relationships [52.72020203771489]
  We investigate target-driven visual navigation using deep reinforcement learning (DRL) in 3D indoor scenes. Our proposed method combines visual features and 3D spatial representations to learn navigation policy. Our experiments, performed in the AI2-THOR, show that our model outperforms the baselines in both SR and SPL metrics.
  arXiv  Detail & Related papers  (2020-04-29T08:46:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.