TacMind: Benchmarking and Modeling Tactile Interaction States for Robotic Manipulation
Overview
This paper presents TacMind, a benchmark in simulation comprising 128 tasks organized into Precise, Recognition, and Dynamic evaluation regimes, along with controlled static/dynamic variants and 12 perturbation settings to assess robustness. The authors propose an action-conditioned latent predictive world model that integrates tactile history to learn a tactile state via prediction of future tactile latents, using this representation to condition action generation and refine candidates through predictive tactile reflection. Experiments demonstrate consistent gains from incorporating tactile information across all evaluated regimes.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Environment: simulation
“tributes under different interaction conditions. In this work, we develop a benchmark in simulation comprising 128 tasks organized around three complementary evaluation regimes: Precise, Recognition, and Dynamic. The benchmark further includes controlled static and dynamic task variants and 12 perturbation settings for evaluating robustness under changes in visual and physical conditions. These settings motivate stud”
Exact source · revision 1Source owner not reported
Report timeline
Follow attributed reports and material updates.
- arXiv Robotics — research abstractsSignalTacMind: Benchmarking and Modeling Tactile Interaction States for Robotic Manipulation
This paper presents TacMind, a benchmark in simulation comprising 128 tasks organized into Precise, Recognition, and Dynamic evaluation regimes, along with controlled static/dynamic variants and 12 perturbation settings to assess robustness. The authors propose an action-conditioned latent predictive world model that integrates tactile history to learn a tactile state via prediction of future tactile latents, using this representation to condition action generation and refine candidates through predictive tactile reflection. Experiments demonstrate consistent gains from incorporating tactile information across all evaluated regimes.
Event coverage history
There is not enough continuous observation data to show a trend.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).