Summary of Detra: a Unified Model For Object Detection and Trajectory Forecasting, by Sergio Casas et al.
DeTra: A Unified Model for Object Detection and Trajectory Forecasting
by Sergio Casas, Ben Agro, Jiageng Mao, Thomas Gilles, Alexander Cui, Thomas Li, Raquel Urtasun
First submitted to arxiv on: 6 Jun 2024
Categories
- Main: Computer Vision and Pattern Recognition (cs.CV)
- Secondary: Artificial Intelligence (cs.AI); Machine Learning (cs.LG); Robotics (cs.RO)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The paper proposes a novel approach for object detection and trajectory forecasting in autonomous driving scenarios. By formulating these tasks as a unified trajectory refinement problem, the model infers the presence, pose, and multi-modal future behaviors of objects directly from LiDAR point clouds and high-definition maps. The designed refinement transformer, called DeTra, outperforms state-of-the-art models on Argoverse 2 Sensor and Waymo Open Dataset by a large margin across various metrics. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Imagine you’re trying to predict where cars will go next in a busy city street. You need to detect the cars first, then figure out their likely paths. This is hard because there’s not much information between the detection and prediction steps. The authors of this paper came up with a new way to solve this problem by combining these two tasks into one. They created a special kind of AI model that can look at LiDAR point clouds (like radar data) and high-definition maps to predict where objects will be in the future. This model, called DeTra, is much better than existing models at predicting what cars will do next. |
Keywords
» Artificial intelligence » Multi modal » Object detection » Transformer
