Long-term autonomy

2 min read

A possible thesis thread: robots that keep working for weeks or months without a person resetting them. The world changes under their maps, their parts wear, and the small faults that never turn up in a demo eventually do.

Change

Maps assume the world holds still. The better systems separate evidence of absence (I looked and the chair wasn’t there) from absence of evidence (I didn’t look). Khronos does this with camera rays, which needs a wall behind the object. See dynamic scenes.

Memory

Scene graphs grow with the data and have only been shown over short runs. Recent memory papers ask what to keep, how far to trust it, and how to tell when it has gone stale. Relocalising against imagery from months or years earlier is still weak, especially under water (underwater perception).

Deployments

Few papers report months in the field: LTR² covers 40 km over six months, and Kairos has eleven months of pedestrian data. Most “long horizon” benchmarks mean a task with many steps (benchmarks).

Faults over time

Faults that come and go, faults that build up slowly, and batteries that run out all look different from the sudden failures most papers test. A safety layer that stops the robot is fine in a demo and expensive in the field, where someone has to go out and reset it. My workshop paper Safe but Stuck is about this. See failure recovery.

Open questions

  1. What counts as evidence that something is gone, outdoors or in open air, where there is no wall behind it?
  2. When should a frequently moved object stop being a node and become a distribution over a room?
  3. How should a robot decide that what it remembers is out of date?
  4. How long does a robot stay useful after its safety layer acts, and can it recover without a person?
  5. Can a team divide the work of re-checking a shared map, so every part gets seen often enough?

Papers

Showing 27 of 27 entries
PaperYearVenueDomain
Hickory2026arXiv preprintland
PSG-Nav2026ICML 2026land
LOST-3DSG2026arXiv preprintland
DAAAM2026CVPR 2026 (per the code README; arXiv lists no venue)land
TrackGraph2026arXiv 2026land, air
3DSG survey2026arXiv preprintgeneral
SuperMap2026RSS 2026land
MERLION2025ICRA 2025sea
Energy-constrained coverage2025arXiv 2025general
SAM 32025arXiv 2025general
AAPD model2025Royal Society Open Science 2025land
CURB-SG2024ICRA 2024land
SAM 22024arXiv 2024general
Hydra (IJRR)2024The International Journal of Robotics Research (IJRR), 2024land
Clio2024IEEE RA-L 2024land
Khronos2024RSS 2024land
SayPlan2023CoRL 2023land
3D VSG2023ICRA 2023land
Embodied AI survey2022IEEE Transactions on Emerging Topics in Computational Intelligence 2022 (arXiv 2021)land
Hydra2022RSS 2022land
DSG navigation policies2021ICRA 2022land
Kimera2021IJRR 2021land
Nav22020IROS 2020land
3D Dynamic Scene Graphs2020RSS 2020land
3DSSG2020CVPR 2020land
Active perception2018Autonomous Robots 42(2), 2018 (arXiv 2016)general
Temporal logic of programs1977FOCS 1977general
Showing 24 of 24 entries
PaperYearVenueDomain
Mapping Pamir2026ICRA 2026sea
Benthic long-term localisation2026Frontiers in Robotics and AI 2026sea
Feel-WM2026arXiv preprintland
T2-Z2026arXiv preprintgeneral
LoGeR2026arXiv 2026general
EvoNav-Bench2026arXiv preprintland
LTR²2026IEEE Transactions on Robotics (accepted)land
MemoGuard2026IEEE Embedded Systems Letters (ESWEEK CODES 2026)land
RIWM2026arXiv preprint (perspective)general
Embodied agent security survey2026arXiv preprint (survey)general
H²-EMV2026arXiv preprintland
Kairos2026arXiv preprintland
Worth Remembering2026arXiv preprintland
SEAM2026arXiv preprintland
OASIS-Map2026arXiv preprintland
Outdoor open-set 3DSGs2026IEEE Transactions on Field Robotics (accepted)land
FOCUS2026arXiv preprintland
ChronoGraph2026arXiv preprintland
UQ-DAAAM2026arXiv preprintland
UW-GS2025WACV 2025sea
V-JEPA 22025arXiv preprintgeneral
Agentic Robot2025arXiv 2025land
Eiffel Tower dataset2023IJRR 2023sea
LIBERO2023arXiv 2023land

Other threads: robust robotics, multi-robot multimodal perception. All three on one page: thesis map.