Related papers: GEM: Gaussian Evolution Model for Occupancy Foreca…
Predicting the future trajectory of agents from visual observations is an important problem for realization of safe and effective navigation of autonomous systems in dynamic environments. This paper focuses on two important aspects of…
We introduce Latent-WAM, an efficient end-to-end autonomous driving framework that achieves strong trajectory planning through spatially-aware and dynamics-informed latent world representations. Existing world-model-based planners suffer…
3D occupancy prediction enables the robots to obtain spatial fine-grained geometry and semantics of the surrounding scene, and has become an essential task for embodied perception. Existing methods based on 3D Gaussians instead of dense…
Recent breakthroughs in autonomous driving have been propelled by advances in robust world modeling, fundamentally transforming how vehicles interpret dynamic scenes and execute safe decision-making. World models have emerged as a linchpin…
Accurate and realistic 3D scene reconstruction enables the lifelike creation of autonomous driving simulation environments. With advancements in 3D Gaussian Splatting (3DGS), previous studies have applied it to reconstruct complex dynamic…
Embodied Vision-Language Models (VLMs) have demonstrated impressive performance and generalization in robotics, particularly within Vision-Language-Action frameworks. However, a significant gap remains between the high-level semantic focus…
Open-vocabulary 3D scene understanding presents a significant challenge in computer vision, with wide-ranging applications in embodied agents and augmented reality systems. Existing methods adopt neurel rendering methods as 3D…
Reliable autonomous driving relies on large-scale, well-labeled data and robust models. However, manual data collection is resource-intensive, and traditional simulation suffers from a persistent reality gap. While recent generative…
Semantic occupancy has emerged as a powerful representation in world models for its ability to capture rich spatial semantics. However, most existing occupancy world models rely on static and fixed embeddings or grids, which inherently…
This paper presents GAMMA, a general motion prediction model that enables large-scale real-time simulation and planning for autonomous driving. GAMMA models heterogeneous, interactive traffic agents. They operate under diverse road…
The sparse object detection paradigm shift towards dense 3D semantic occupancy prediction is necessary for dealing with long-tail safety challenges for autonomous vehicles. Nonetheless, the current voxelization methods commonly suffer from…
Detection and segmentation of moving obstacles, along with prediction of the future occupancy states of the local environment, are essential for autonomous vehicles to proactively make safe and informed decisions. In this paper, we propose…
The field of autonomous driving is experiencing a surge of interest in world models, which aim to predict potential future scenarios based on historical observations. In this paper, we introduce DFIT-OccWorld, an efficient 3D occupancy…
3D semantic occupancy prediction is crucial for autonomous driving. While multi-modal fusion improves accuracy over vision-only methods, it typically relies on computationally expensive dense voxel or BEV tensors. We present Gau-Occ, a…
Open-world 3D semantic occupancy prediction aims to generate a voxelized 3D representation from sensor inputs while recognizing both known and unknown objects. Transferring open-vocabulary knowledge from vision-language models (VLMs) offers…
Vision-language-action (VLA) policies have advanced language-conditioned robotic manipulation by transferring semantic priors from pretrained vision-language models to action generation. However, standard action-imitation learning often…
Dynamic scene rendering opens new avenues in autonomous driving by enabling closed-loop simulations with photorealistic data, which is crucial for validating end-to-end algorithms. However, the complex and highly dynamic nature of traffic…
Advanced end-to-end autonomous driving systems predict other vehicles' motions and plan ego vehicle's trajectory. The world model that can foresee the outcome of the trajectory has been used to evaluate the autonomous driving system.…
Autonomous agents rely on sensor data to construct representations of their environments, essential for predicting future events and planning their actions. However, sensor measurements suffer from limited range, occlusions, and sensor…
Embodied scene understanding serves as the cornerstone for autonomous agents to perceive, interpret, and respond to open driving scenarios. Such understanding is typically founded upon Vision-Language Models (VLMs). Nevertheless, existing…