相关论文: Modernising Reinforcement Learning-Based Navigatio…

Despite rapid progress, embodied agents still struggle with long-horizon manipulation that requires maintaining spatial consistency, causal dependencies, and goal constraints. A key limitation of existing approaches is that task reasoning…

This paper focuses on visual semantic navigation, the task of producing actions for an active agent to navigate to a specified target object category in an unknown environment. To complete this task, the algorithm should simultaneously…

Generating adversarial scenarios, which have the potential to fail autonomous driving systems, provides an effective way to improve robustness. Extending purely data-driven generative models, recent specialized models satisfy additional…

Semantic scene completion (SSC) aims to predict the semantic occupancy of each voxel in the entire 3D scene from limited observations, which is an emerging and critical task for autonomous driving. Recently, many studies have turned to…

While Large Language Models (LLMs) have demonstrated strong zero-shot reasoning capabilities, their deployment as embodied agents still faces fundamental challenges in long-horizon planning. Unlike open-ended text generation, embodied…

Spatial reasoning in partially observable environments has often been approached through passive predictive models, yet theories of embodied cognition suggest that genuinely useful representations arise only when perception is tightly…

Visual Navigation is a core task in Embodied AI, enabling agents to navigate complex environments toward given objectives. Across diverse settings within Navigation tasks, many necessitate the modelling of sequential data accumulated from…

Embodied navigation requires agents to integrate perception, reasoning, and action for robust interaction in complex 3D environments. Existing approaches often suffer from incoherent and unstable reasoning traces that hinder generalization…

Visual object navigation using learning methods is one of the key tasks in mobile robotics. This paper introduces a new representation of a scene semantic map formed during the embodied agent interaction with the indoor environment. It is…

This paper presents a framework for multi-agent navigation in structured but dynamic environments, integrating three key components: a shared semantic map encoding metric and semantic environmental knowledge, a claim policy for coordinating…

This paper introduces a novel semantics-aware inspection planning policy derived through deep reinforcement learning. Reflecting the fact that within autonomous informative path planning missions in unknown environments, it is often only a…

Vehicle detection and localization in complex traffic scenarios pose significant challenges due to the interference of moving objects. Traditional methods often rely on outlier exclusions or semantic segmentations, which suffer from low…

In this study, we focus on the graph representation learning (a.k.a. network embedding) in attributed graphs. Different from existing embedding methods that treat the incorporation of graph structure and semantic as the simple combination…

Embodied visual navigation remains a challenging task, as agents must explore unknown environments with limited knowledge. Existing zero-shot studies have shown that incorporating memory mechanisms to support goal-directed behavior can…

A novel framework is proposed to incrementally collect landmark-based graph memory and use the collected memory for image goal navigation. Given a target image to search, an embodied robot utilizes semantic memory to find the target in an…

Graph based representation has been widely used in modelling spatio-temporal relationships in video understanding. Although effective, existing graph-based approaches focus on capturing the human-object relationships while ignoring…

Representing a dynamic scene using a structured spatial-temporal scene graph is a novel and particularly challenging task. To tackle this task, it is crucial to learn the temporal interactions between objects in addition to their spatial…

Representations are crucial for a robot to learn effective navigation policies. Recent work has shown that mid-level perceptual abstractions, such as depth estimates or 2D semantic segmentation, lead to more effective policies when provided…

Scene graphs provide valuable information to many downstream tasks. Many scene graph generation (SGG) models solely use the limited annotated relation triples for training, leading to their underperformance on low-shot (few and zero)…

Navigating urban environments represents a complex task for automated vehicles. They must reach their goal safely and efficiently while considering a multitude of traffic participants. We propose a modular decision making algorithm to…