cd /news/robotics/coding-agents-with-an-obstacle-aware… · home topics robotics article
[ARTICLE · art-133807] src=arxiv.org ↗ pub= topic=robotics verified=true sentiment=↑ positive

Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation

A September 17, 2026 arXiv paper (2609.20822v1) reports that coding agents tasked with robot manipulation collide with a forbidden obstacle in most cases because the safety constraint never becomes a planning priority, not because of perception or instruction failures. The authors introduce SafeHarness, which adds obstacle-aware route planning and obstacle-aware contact execution, achieving 71.9% task success and 87.5% collision avoidance, surpassing the previous state of the art by 6.5% and 27.0% respectively — 2.3x and 1.5x the same agent without harnesses.

read2 min views3 publishedSep 18, 2026
Coding Agents with an Obstacle-Aware Harness for Safe Robot Manipulation
Image: source
  [Submitted on 17 Sep 2026]


[View PDF](http://arxiv.org/pdf/2609.20822v1)

[HTML (experimental)](https://arxiv.org/html/2609.20822v1)

Abstract:Coding agents have emerged as a promising paradigm for robot manipulation: a language model writes the robot controller as a program, and agents built in this way now operate robots without robot-specific this http URL this paradigm is also safe, however, has not been asked. We evaluate coding agent under a safety constraint, where each task pairs a manipulation goal with an obstacle the robot must not touch. The agent pursues the goal but collides with the obstacle in most cases, treating task completion as its sole objective while neglecting safety. The agent reasons about the obstacle in its traces, and the prompt already forbids touching it, so neither perception nor instruction is at fault; the fault lies in the planning, where the stated constraint never becomes a priority. By decomposing manipulation into a route phase and a contact-rich moment, we locate the source of the failure. Along the route, the model cannot prioritize the safety constraint, having no notion of a clearing route and none of replanning once a chosen route becomes infeasible. At the contact, it is unaware that contact execution is bounded by the same constraint. To close this gap, we present SafeHarness, which equips the model with two obstacle-aware harnesses that enable it to prioritize the safety constraint. Obstacle-aware route planning grounds the objects as bounding boxes and draws candidate routes over them as sequences of waypoints. The agent then plans a route in advance, verifies it, replans when necessary, and only then executes it. Obstacle-aware contact execution instead selects the contact position so that the contact itself avoids the obstacle. SafeHarness attains 71.9% task success and 87.5% collision avoidance, surpassing the previous SOTA by 6.5% and 27.0%, respectively. These results are $2.3\times$ and $1.5\times$ those of the same agent without harnesses.

Current browse context:

cs.RO

References & Citations

...

Bibliographic Explorer

(What is the Explorer?) Connected Papers

(What is Connected Papers?) Litmaps

(What is Litmaps?) scite Smart Citations

(What are Smart Citations?) alphaXiv

(What is alphaXiv?) CatalyzeX Code Finder for Papers

(What is CatalyzeX?) DagsHub

(What is DagsHub?) Gotit.pub

(What is GotitPub?) Hugging Face

(What is Huggingface?) ScienceCast

(What is ScienceCast?) Influence Flower

(What are Influence Flowers?) CORE Recommender

(What is CORE?) arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.

── more in #robotics 4 stories · sorted by recency
── more on @safeharness 3 stories trending now
sponsored brought to you by zahid.host 4,200+ EU-deployed projects
reading about agents? ship yours in a single git push.

Run your AI side-project on zahid.host

EU-based hosting, git-push deploys, automatic HTTPS, no cold starts. Free tier with a custom domain — perfect for shipping the agent you just read about.

$git push zahid main
Live at https://your-agent.zahid.host
Get free account → Pricing
from €0/mo · no card required
LIVE [news/coding-agents-with-a…] indexed:0 read:2min 2026-09-18 ·