Learning Object Relation Graph and Tentative Policy for Visual Navigation

By Heming Du, Xin Yu, Liang Zheng. 2020

171 citations recorded by the source corpus.

Target-driven visual navigation aims at navigating an agent towards a given target based on the observation of the agent. In this task, it is critical to learn informative visual representation and robust navigation policy. Aiming to improve these two components, this paper proposes three complementary techniques, object relation graph (ORG), trial-driven imitation learning (IL), and a memory-augmented tentative policy network (TPN). ORG improves visual representation learning by integrating object relationships, including category closeness and spatial correlations, e.g., a TV usually co-occurs with a remote spatially. Both Trial-driven IL and TPN underlie robust navigation policy, instructing the agent to escape from deadlock states, such as looping or being stuck. Specifically, trial-driven IL is a type of supervision used in policy network training, while TPN, mimicking the IL supervision in unseen environment, is applied in testing. Experiment in the artificial environment AI2-Thor validates that each of the techniques is effective. When combined, the techniques bring significantly improvement over baseline methods in navigation effectiveness and efficiency in unseen environments. We report 22.8% and 23.5% increase in success rate and Success weighted by Path Length (SPL), respectively. The code is available at this https URL.

Subfields: Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

Citations in the corpus

Continuous Scene Representations for Embodied AI (2022, methodology): “Our method is closer to the approaches that create scene graphs in embodied or physics based settings [6, 17, 31, 39, 67].”
A Survey of Embodied AI: From Simulators to Research Tasks (2021, methodology): “Examples of down-stream tasks that make use of visual exploration outputs (i.e. maps) include Image Navigation [26], [73], Point Navigation [11], [44] and Object Navigation [53], [54], [56].”
Pushing it out of the Way: Interactive Visual Navigation (2021, background): “Most works focus on point navigation (PointNav) [3, 9, 29, 38] or object navigation (ObjectNav) [5, 8, 10, 39].”
Embodied Semantic Scene Graph Generation (2021, background): “Du et al. [24] proposes to learn object relation graph and tentative policy for visual navigation.”
Room-and-Object Aware Knowledge Reasoning for Remote Embodied Referring Expression (2021, methodology): “Numerous methods [47, 48, 19, 7, 12, 10, 46, 36, 17, 20] have been proposed to address the VLN task.”