Related papers: AstraNav-World: World Model for Foresight Control …

In Vision-and-Language Navigation (VLN), an embodied agent needs to reach a target destination with the only guidance of a natural language instruction. To explore the environment and progress towards the target location, the agent must…

Future trajectories of neighboring traffic agents have a significant influence on the path planning and decision-making of autonomous vehicles. While trajectory forecasting is a well-studied field, research mainly focuses on snapshot-based…

Pretrained video generation models provide strong priors for robot control, but existing unified world action models still struggle to decode reliable actions without substantial robot-specific training. We attribute this limitation to a…

World models are becoming central to robotic planning and control as they enable prediction of future state transitions. Existing approaches often emphasize video generation or natural-language prediction, which are difficult to ground in…

Diffusion models have demonstrated exceptional visual quality in video generation, making them promising for autonomous driving world modeling. However, existing video diffusion-based world models struggle with flexible-length, long-horizon…

The integration of geometric reconstruction and generative modeling remains a critical challenge in developing AI systems capable of human-like spatial reasoning. This paper proposes Aether, a unified framework that enables geometry-aware…

We present a target-driven navigation system to improve mapless visual navigation in indoor scenes. Our method takes a multi-view observation of a robot and a target as inputs at each time step to provide a sequence of actions that move the…

While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reasoning. Existing embodied benchmarks largely focus on passive, static household environments and…

Previous Vision-Language-Action models face critical limitations in navigation: scarce, diverse data from labor-intensive collection and static representations that fail to capture temporal dynamics and physical laws. We propose NavDreamer,…

Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control interfaces from unlabeled video, learned latents often fail to transfer across contexts: they…

Visual navigation is fundamental to autonomous systems, yet generating reliable trajectories in cluttered and uncertain environments remains a core challenge. Recent generative models promise end-to-end synthesis, but their reliance on…

Realizing active visual tracking with a single unified model across diverse robots is challenging, as the physical constraints and motion dynamics vary drastically from one platform to another. Existing approaches typically train separate…

Real-world driving requires people to observe the current environment, anticipate the future, and make appropriate driving decisions. This requirement is aligned well with the capabilities of world models, which understand the environment…

General-purpose navigation in challenging environments remains a significant problem in robotics, with current state-of-the-art approaches facing myriad limitations. Classical approaches struggle with cluttered settings and require…

Recent successes in autoregressive (AR) generation models, such as the GPT series in natural language processing, have motivated efforts to replicate this success in visual tasks. Some works attempt to extend this approach to autonomous…

Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…

Collaborative navigation becomes essential in situations of occluded scenarios in autonomous driving where independent driving policies are likely to lead to collisions. One promising approach to address this issue is through the use of…

Generalist robot policies can now perform a wide range of manipulation skills, but evaluating and improving their ability with unfamiliar objects and instructions remains a significant challenge. Rigorous evaluation requires a large number…

Embodied intelligence is often studied through specialized models for individual tasks such as manipulation or navigation, resulting in fragmented capabilities and limited generalization across tasks, environments, and robot embodiments. In…

A world model enables an intelligent agent to imagine, predict, and reason about how the world evolves in response to its actions, and accordingly to plan and strategize. While recent video generation models produce realistic visual…