Researchers Develop Tactile-Only Blind Grasping System for Dexterous Robotic Hands
Researchers have proposed a framework enabling a multi-fingered robotic hand to grasp objects using only tactile sensing, without any visual input or real-world demonstrations. The system combines a Real2Sim tactile calibration pipeline, a layout-aware tactile encoder, and a diffusion-based policy trained in simulation, then deployed on a physical LEAP Hand. The work addresses a longstanding challenge in robotics—bridging the simulation-to-real gap for tactile sensing—and could advance manipulation capabilities in unstructured or visually occluded environments.
A team of researchers has introduced a Real2Sim2Real framework for blind dexterous grasping, enabling a robotic hand to manipulate objects using tactile signals alone. The approach centers on three components: a Real2Sim calibration pipeline that builds a contact-calibrated digital-twin simulator to reproduce real tactile signals, a layout-aware tactile encoder that uses sensor-geometry priors via self-supervised pretraining to improve the expressiveness of sparse tactile data, and a Diffusion Policy trained by aggregating successful trajectories from object-specific reinforcement-learning experts in simulation. The system was evaluated on a physical LEAP Hand with distributed tactile sensing across 20 objects—10 seen and 10 unseen during training—achieving a 27% real-world grasp success rate without any real-world grasping demonstrations or visual input. Simulation ablations confirmed that layout-aware tactile pretraining improves grasping performance, and sensing-level evaluations validated that Real2Sim calibration increases consistency between simulated and hardware tactile contact events. The authors argue that combining contact-event calibration, geometry-aware tactile representation learning, and diffusion-based policy aggregation offers a viable path toward tactile-only blind grasping on real dexterous robotic hands.
What's missing
The paper does not appear to break down success rates separately for seen versus unseen objects in the abstract, making it difficult to assess generalization performance independently from the abstract alone. No comparison to a visual-input baseline or prior tactile-only methods is mentioned in the abstract, limiting benchmarking context.
What different sources said
- arXiv cs.AICenter
Blind Dexterous Grasping via Real2Sim2Real Tactile Policy Learning
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.