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

Embodied agents often struggle with efficient navigation because they rely primarily on partial egocentric observations, which restrict global foresight and lead to inefficient exploration. In contrast, humans plan using maps: we reason…

Action-conditioned robot world models generate future video frames of the manipulated scene given a robot action sequence, offering a promising alternative for simulating tasks that are difficult to model with traditional physics engines.…

Deploying autonomous agents in real world environments is challenging, particularly for navigation, where systems must adapt to situations they have not encountered before. Traditional learning approaches require substantial amounts of…

End-to-end autonomous driving planners typically generate trajectories from current observations alone. However, real-world driving is highly dynamic, and such reactive planning cannot anticipate future scene evolution, often leading to…

Robust autonomous navigation for Autonomous Aerial Vehicles (AAVs) in complex environments is a critical capability. However, modern end-to-end navigation faces a key challenge: the high-frequency control loop needed for agile flight…

Vision-and-Language Navigation (VLN) is a cornerstone of embodied intelligence. However, current agents often suffer from significant performance degradation when transitioning from simulation to real-world deployment, primarily due to…

World models aim to endow AI systems with the ability to represent, generate, and interact with dynamic environments in a coherent and temporally consistent manner. While recent video generation models have demonstrated impressive visual…

Robotic imitation learning has advanced from solving static tasks to addressing dynamic interaction scenarios, but testing and evaluation remain costly and challenging due to the need for real-time interaction with dynamic environments. We…

Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…

Video-based world models offer a powerful paradigm for embodied simulation and planning, yet state-of-the-art models often generate physically implausible manipulations - such as object penetration and anti-gravity motion - due to training…

Current end-to-end autonomous driving planners are fundamentally reactive: they condition on historical and present observations to predict future actions. We argue that autonomous agents should instead imagine future scenes before…

World models learn the consequences of actions in vision-based interactive systems. However, in practical scenarios such as autonomous driving, there commonly exists noncontrollable dynamics independent of the action signals, making it…

Learning predictive world models from raw visual observations is a central challenge in reinforcement learning (RL), especially for robotics and continuous control. Conventional model-based RL frameworks directly condition future…

End-to-end autonomous driving systems increasingly rely on vision-centric world models to understand and predict their environment. However, a common ineffectiveness in these models is the full reconstruction of future scenes, which expends…

General-purpose world models promise scalable policy evaluation, optimization, and planning, yet achieving the required level of robustness remains challenging. Unlike policy learning, which primarily focuses on optimal actions, a world…

Vision-language navigation (VLN) requires intelligent agents to navigate environments by interpreting linguistic instructions alongside visual observations, serving as a cornerstone task in Embodied AI. Current VLN research for unmanned…

Predictive foresight is important to intelligent embodied agents. Since the motor execution of a robot is intrinsically constrained by its visual perception of environmental geometry, effectively anticipating the future requires capturing…

Enhancing the spatial perception capabilities of mobile robots is crucial for achieving embodied Vision-and-Language Navigation (VLN). Although significant progress has been made in simulated environments, directly transferring these…

Recent advances in robot foundation models trained on large-scale human teleoperation data have enabled robots to perform increasingly complex real-world tasks. However, scaling these systems remains difficult because collecting…

Vision-Language-Action (VLA) models are a promising path toward embodied intelligence, yet they often overlook the predictive and temporal-causal structure underlying visual dynamics. World-model VLAs address this by predicting future…