CHOP: Counterfactual Human Preference Labels Improve Obstacle Avoidance in Visuomotor Navigation Policies
CHOP: Counterfactual Human Preference Labels Improve Obstacle Avoidance in Visuomotor Navigation Policies
This paper presents CHOP, a novel approach that utilizes counterfactual human preference labels to align visuomotor navigation policies with human intuition regarding safety and obstacle avoidance.
The study introduces CHOP, a method using counterfactual human preference labels to improve obstacle avoidance in visuomotor navigation policies, with results demonstrated on the SCAND dataset and transferred to real-world deployment on a Ghost Robotics Vision60 quadruped.
Source: arXiv Robotics — research abstracts · Read original article ↗
Loading article text…
What the source reports
Publisher-reported claims, with original evidence. These results have not been independently verified by RoboSignal.
- Data origin
- Robot trajectoriesOpen source S3
Reported numbers
Reported success rate
24.4%
Reported trials
View original evidence
e-of-the-art models, compared to their pretrained baselines. These improvements transfer to real-world deployments on a Ghost Robotics Vision60 quadruped, where CHOP-aligned policies improve average goal success rates by 24.4%, increase minimum obstacle clearance by 6.8%, reduce collision and intervention events by 45.7%, and improve normalized path completion by 38.6% on average across navigation scenarios, compared
Open source S5
- paper: not_reported
What remains unknown
Not established in the collected evidence: Environment, Control.
Reported performance applies to the described task. It does not establish general autonomy or deployment readiness.
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
e-of-the-art models, compared to their pretrained baselines. These improvements transfer to real-world deployments on a Ghost Robotics Vision60 quadruped, where CHOP-aligned policies improve average goal success rates by 24.4%, increase minimum obstacle clearance by 6.8%, reduce collision and intervention events by 45.7%, and improve normalized path completion by 38.6% on average across navigation scenarios, compared
Open source S5
fety and obstacle avoidance in navigation. In CHOP, for each visual observation, the robot's executed trajectory is included among a set of counterfactual navigation trajectories: alternative trajectories the robot could have followed under identical conditions. Human annotators provide pairwise preference labels over these trajectories based on anticipated outcomes such as collision risk and path efficiency. These a
Open source S3
ggregated preferences are then used to fine-tune visuomotor navigation policies, aligning their behavior with human preferences in navigation. Experiments on the SCAND dataset show that visuomotor navigation policies fine-tuned with CHOP reduce near-collision events by 49.7%, decrease deviation from human-preferred trajectories by 45.0%, and increase average obstacle clearance by 19.8% on average across multiple stat
Open source S4
Implications for data suppliers
RoboSignal interpretation and collection questions, not statements of buyer demand.
- Match the buyer’s robot embodiment, action space, sensors and timestamp requirements before planning collection.
- Compare the reported units and scope before using these quantities in a budget. Recording hours, sensor-hours and trajectories are different measures.
- Validate demand and acceptance criteria with a buyer before scaling. Publication, popularity and a research result do not establish a purchase commitment.
Source：arXiv Robotics — research abstracts · arxiv.org