pith. sign in
Pith Number

pith:REHXFOZW

pith:2023:REHXFOZW6PXSQEBZLYBBMSPWUZ
not attested not anchored not stored refs resolved

Rethinking the Open-Loop Evaluation of End-to-End Autonomous Driving in nuScenes

Jiang-Jiang Liu, Jiang-Tian Zhai, Jingdong Wang, Jinhao Du, Xiaoqing Ye, Yifu Zhang, Yongqiang Mao, Ze Feng, Zichang Tan

A simple MLP using only past trajectories and velocity matches perception-based planners on nuScenes L2 error.

arxiv:2305.10430 v2 · 2023-05-17 · cs.CV

Add to your LaTeX paper
\usepackage{pith}
\pithnumber{REHXFOZW6PXSQEBZLYBBMSPWUZ}

Prints a linked badge after your title and injects PDF metadata. Compiles on arXiv. Learn more · Embed verified badge

Record completeness

1 Bitcoin timestamp
2 Internet Archive
3 Author claim open · sign in to claim
4 Citations open
5 Replications open
Portable graph bundle live · download bundle · merged state
The bundle contains the canonical record plus signed events. A mirror can host it anywhere and recompute the same current state with the deterministic merge algorithm.

Claims

C1strongest claim

Our simple method achieves similar end-to-end planning performance on the nuScenes dataset with other perception-based methods, reducing the average L2 error by about 20%.

C2weakest assumption

That the MLP baseline is trained and evaluated under identical conditions and data splits as the perception-based competitors, with no hidden advantages from trajectory history alone.

C3one line summary

A perception-free MLP reduces average L2 trajectory error by ~20% versus perception-based methods on nuScenes, suggesting current open-loop evaluation may reward trajectory mimicry over safe planning.

References

18 extracted · 18 resolved · 0 Pith anchors

[1] nuscenes: A multi- modal dataset for autonomous driving 2020
[2] What data do we need for train- ing an A V motion planner? InICRA, 2021 2021
[3] Transfuser: Imitation with transformer-based sensor fusion for autonomous driv- ing 2022
[4] Densetnt: End-to-end trajectory prediction from dense goal sets 2021
[5] FIERY: Future instance segmentation in bird’s-eye view from surround monocular cameras

Formal links

2 machine-checked theorem links

Cited by

28 papers in Pith

Receipt and verification
First computed 2026-05-17T23:38:14.595898Z
Builder pith-number-builder-2026-05-17-v1
Signature Pith Ed25519 (pith-v1-2026-05) · public key
Schema pith-number/v1.0

Canonical hash

890f72bb36f3ef2810395e021649f6a66e3e9ca152edf2253b4fb890297ce186

Aliases

arxiv: 2305.10430 · arxiv_version: 2305.10430v2 · doi: 10.48550/arxiv.2305.10430 · pith_short_12: REHXFOZW6PXS · pith_short_16: REHXFOZW6PXSQEBZ · pith_short_8: REHXFOZW
Agent API
Verify this Pith Number yourself
curl -sH 'Accept: application/ld+json' https://pith.science/pith/REHXFOZW6PXSQEBZLYBBMSPWUZ \
  | jq -c '.canonical_record' \
  | python3 -c "import sys,json,hashlib; b=json.dumps(json.loads(sys.stdin.read()), sort_keys=True, separators=(',',':'), ensure_ascii=False).encode(); print(hashlib.sha256(b).hexdigest())"
# expect: 890f72bb36f3ef2810395e021649f6a66e3e9ca152edf2253b4fb890297ce186
Canonical record JSON
{
  "metadata": {
    "abstract_canon_sha256": "d4ae155f41e9d06c0e9da8f5177f1554cae68f39b690e191977bd2e5ddc01ed2",
    "cross_cats_sorted": [],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "primary_cat": "cs.CV",
    "submitted_at": "2023-05-17T17:59:11Z",
    "title_canon_sha256": "f6387b9d58db4b8d251016b2a10cacce8ebb26ce09331af8f03cb56a5f177f45"
  },
  "schema_version": "1.0",
  "source": {
    "id": "2305.10430",
    "kind": "arxiv",
    "version": 2
  }
}