{
  "id": "2101.06679",
  "version": "v1",
  "published": "2021-01-17T14:16:12.000Z",
  "updated": "2021-01-17T14:16:12.000Z",
  "title": "End-to-end Interpretable Neural Motion Planner",
  "authors": [
    "Wenyuan Zeng",
    "Wenjie Luo",
    "Simon Suo",
    "Abbas Sadat",
    "Bin Yang",
    "Sergio Casas",
    "Raquel Urtasun"
  ],
  "comment": "CVPR 2019 (Oral)",
  "categories": [
    "cs.CV",
    "cs.RO"
  ],
  "abstract": "In this paper, we propose a neural motion planner (NMP) for learning to drive autonomously in complex urban scenarios that include traffic-light handling, yielding, and interactions with multiple road-users. Towards this goal, we design a holistic model that takes as input raw LIDAR data and a HD map and produces interpretable intermediate representations in the form of 3D detections and their future trajectories, as well as a cost volume defining the goodness of each position that the self-driving car can take within the planning horizon. We then sample a set of diverse physically possible trajectories and choose the one with the minimum learned cost. Importantly, our cost volume is able to naturally capture multi-modality. We demonstrate the effectiveness of our approach in real-world driving data captured in several cities in North America. Our experiments show that the learned cost volume can generate safer planning than all the baselines.",
  "revisions": [
    {
      "version": "v1",
      "updated": "2021-01-17T14:16:12.000Z"
    }
  ],
  "analyses": {
    "keywords": [
      "end-to-end interpretable neural motion planner",
      "cost volume",
      "input raw lidar data",
      "learned cost",
      "complex urban scenarios"
    ],
    "note": {
      "typesetting": "TeX",
      "pages": 0,
      "language": "en",
      "license": "arXiv",
      "status": "editable"
    }
  }
}