aiqbench analysis
TriO advances autonomous driving perception by introducing a tri-modal unsupervised world model that fuses camera, LiDAR, and RADAR data to predict 4D occupancy without human annotations. This approach significantly improves the segmentation of long-tail objects and achieves state-of-the-art results in flow prediction and obstacle detection across multiple datasets. The research demonstrates a robust method for handling open-set scenarios where traditional supervised learning struggles with rare or unseen obstacles.
TriO: Tri-Modal Unsupervised Occupancy World Model for Anything Perception
arXiv:2609.32013v1 Announce Type: cross Abstract: We present TriO, a multi-modal unsupervised world model that predicts 4D occupancy, obstacle segmentation, flow and LiDAR. In contrast to prior work, TriO utilizes three distinct sensor modalities (camera, LiDAR, and RADAR) as both inputs and sources of self-supervision, eliminating the need for additional human annotations. Thanks to its novel supervision, the model is able to segment any occupancy from the drivable surface, overcoming the limitations of existing open-set methods in handling long-tail objects. TriO achieves state-of-the-art results in multiple 3D and 4D tasks, including occupancy, flow, and LiDAR prediction, as well as zero-shot road obstacle segmentation across multiple datasets such as Argoverse 2, and Spotting the Unexpected.
Abstract:We present TriO, a multi-modal unsupervised world model that predicts 4D occupancy, obstacle segmentation, flow and LiDAR. In contrast to prior work, TriO utilizes three distinct sensor modalities (camera, LiDAR, and RADAR) as both inputs and sources of self-supervision, eliminating the need for additional human annotations. Thanks to its novel supervision, the model is able to segment any occupancy from the drivable surface, overcoming the limitations of existing open-set methods in handling long-tail objects. TriO achieves state-of-the-art results in multiple 3D and 4D tasks, including occupancy, flow, and LiDAR prediction, as well as zero-shot road obstacle segmentation across multiple datasets such as Argoverse 2, and Spotting the Unexpected.
Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI)
arXiv:2609.32013 [cs.CV]
(or arXiv:2609.32013v1 [cs.CV] for this version)
https://doi.org/10.48550/arXiv.2609.32013 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 208 words
Related coverage
Dyna-2: General Purpose Physical Agents with Hour-Long Autonomy — Jason Ma, Dyna Robotics
Latent Space · Oct 13, 2026
Concrete Evaluations to Investigate the OpenAI Model That Hacked Hugging Face
AI Alignment Forum · Aug 3, 2026
O3N: Omnidirectional Open-Vocabulary Occupancy Prediction
arXiv · Jul 23, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026