Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation
Spark-0: Scaling Spatially Aligned Tactile Pretraining for Robot Dexterous Manipulation
Spark-0 is a vision-tactile-language-action model that leverages tactile data to enhance robot dexterous manipulation. The model uses a 1,000-hour tactile dataset, HumanTouch, and combines it with visual data and simulation for pretraining. It achieves the highest mean success rate on SparkArena and improves success rates on both simulated and real-world tasks when tactile data is included.
Spark-0 introduces a vision-tactile-language-action model that combines tactile data with visual pretraining to improve dexterous manipulation. The paper reports significant improvements in success rates when tactile data is included, suggesting its value as both a policy input and a supervisory signal.
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.
Reported numbers
Reported duration
1,000 hours
- paper: not_reported
- code: not_reported
- weights: not_reported
- dataset: not_reported
Source excerpts and review record
Automatically extracted; no manual editorial approval recorded.
h, a 1,000-hour dataset of full-hand tactile human manipulation, and pretrain Spark-0 on it together with egocentric video, robot data, and simulation. We also release SparkArena, which pairs vision-only simulated tasks with tactile-conditioned real-robot tasks on one dexterous embodiment. Spark-0 achieves the highest mean success rate on both SparkArena tracks and ranks first on all eight aggregate metrics of the Eg
Open source S4
o Humanoid Manipulation Benchmark. Compared with vision-only pretraining on the same data and compute with touch discarded, retaining the touch of 1,000 hours of HumanTouch raises vision-only success on Ego Humanoid from 52.5% to 71.7%, and success on SparkArena-Real, where touch is also used at deployment, from 44.0% to 52.0%, indicating that touch serves not only as a policy input but also as scalable supervision f
Open source S5
Source：arXiv Robotics — research abstracts · arxiv.org