MultiON
Simulation benchmark where an agent must find several target objects in a set order in 3D homes.1
Last checked 10 Oct 2026Basic entry15 of 21 facts checked at the sourceNext check 8 Apr 2027
Runs in
Simulation2
Checked against real robots
Not checked
Skill
Navigation
Robot
Wheels only3
Licence
Unclear5
Comparisons with real robots
No comparison found Unknown
Details
No real-robot evaluation in the paper or challenge pages; none found in a web search.
Details
About
- What it is
- Benchmark Inferred1
More
Classified by the Atlas from how the authors describe and distribute it.
- Built by
- IIT Kanpur, UIUC, Simon Fraser University (paper); challenge hosted by SFU (3dlg-hcvc, EvalAI team 'Multion Team', sfu-evalai)3
More
Challenge host from https://eval.ai/api/challenges/challenge/2276/
- Released
- 2020-12 (arXiv v1 2020-12-07)1
- Version
- 2024 task: 3 targets per episode described by language (e.g. 'Find the mantel clock on the chest of drawers'), goal set not known a priori, HSSD scenes2
- Last update
- MultiON Challenge 2024 at CVPR 2024 Embodied AI Workshop (start 2024-04-19, deadline 2024-06-03); EvalAI challenge 2276 '2024-2025' ran to 2025-08-01; challenge repo last commit 2024-05-302
More
EvalAI dates: https://eval.ai/api/challenges/challenge/2276/
- Status
- Dormant Inferred2
More
Last edition 2024; EvalAI closed 2025-08-01; no 2025/2026 edition listed on the challenge site.
Setup
Scoring and access
- Scored by
- Progress score, Path efficiency, Success rate2
More
Definitions also in https://arxiv.org/pdf/2012.03912v1
- Who runs it
- The organisers run the tests2
- Leaderboard
- Official leaderboard6
- Code licence
- MIT (3dlg-hcvc/multion-challenge); original saimwani/multiON repo has no licence per GitHub5
More
Original repo: https://api.github.com/repos/saimwani/multiON
- Data licence
- Unknown
More
Looked at challenge site Terms and Conditions and repo READMEs.
Sources 6
- 1MultiON: Benchmarking Semantic Map Memory using Multi-Object NavigationPaper · Dec 2020 · checked 10 Oct 2026
- 2MultiON EAI Challenge CVPR 2024Official site · checked 10 Oct 2026
- 3MultiON: Benchmarking Semantic Map Memory using Multi-Object NavigationPaper · Dec 2020 · checked 10 Oct 2026
- 4Semantic Scholar API recordIndex · checked 10 Oct 2026
- 53dlg-hcvc/multion-challenge on GitHub (repository)Repository · checked 10 Oct 2026
- 6EvalAI: Evaluating state of the art in AILeaderboard · checked 10 Oct 2026
Change history
- Created as a basic entry: identity facts checked at primary sources (phase 1 re-verification).