analiza aiqbench
This research introduces a bio-inspired whisker-based tactile system that enables sub-10-gram drones to navigate autonomously using touch rather than vision, addressing critical limitations in GPS-denied or dark environments. By running entirely on a microcontroller with minimal memory, the approach demonstrates how lightweight hardware can achieve millimeter-scale depth estimation for obstacle avoidance and surface contouring. This advancement expands the operational envelope of small-scale robotics beyond visual sensing constraints.
Whisker-based Tactile Flight for Tiny Drones
arXiv:2510.03119v2 Announce Type: replace Abstract: Tiny flying robots hold great potential for search-and-rescue, safety inspections, and environmental monitoring, but their small size and limited computational resources constrain onboard sensing capabilities. Inspired by animals such as rats and moles, which rely on lightweight whiskers to navigate and perceive their surroundings through touch, we present a 3.2-gram whisker-based tactile sensing apparatus that enables tiny drones to perceive and interact with their environment through gentle physical contact, even in complete darkness. The apparatus employs barometers at the base of each whisker to estimate contact depth, enabling obstacle localization while minimizing contact-induced destabilization. To compensate for sensor noise and drift during sustained contact, we develop a tactile depth estimation pipeline that achieves millimeter-scale depth estimation accuracy. Together, these innovations enable tiny drones to autonomously avoid obstacles, contour surfaces, and explore confined spaces, guided by onboard tactile sensing across both rigid and soft environments. Running entirely onboard a microcontroller with just 192 KB of memory, our system demonstrates autonomous tactile flight across various scenarios. This bio-inspired approach extends perception for mobile robots beyond vision, opening new possibilities for autonomous operations in visually degraded and GPS-denied environments.
Abstract:Tiny flying robots hold great potential for search-and-rescue, safety inspections, and environmental monitoring, but their small size and limited computational resources constrain onboard sensing capabilities. Inspired by animals such as rats and moles, which rely on lightweight whiskers to navigate and perceive their surroundings through touch, we present a 3.2-gram whisker-based tactile sensing apparatus that enables tiny drones to perceive and interact with their environment through gentle physical contact, even in complete darkness. The apparatus employs barometers at the base of each whisker to estimate contact depth, enabling obstacle localization while minimizing contact-induced destabilization. To compensate for sensor noise and drift during sustained contact, we develop a tactile depth estimation pipeline that achieves millimeter-scale depth estimation accuracy. Together, these innovations enable tiny drones to autonomously avoid obstacles, contour surfaces, and explore confined spaces, guided by onboard tactile sensing across both rigid and soft environments. Running entirely onboard a microcontroller with just 192 KB of memory, our system demonstrates autonomous tactile flight across various scenarios. This bio-inspired approach extends perception for mobile robots beyond vision, opening new possibilities for autonomous operations in visually degraded and GPS-denied environments.
Robotics (cs.RO)
arXiv:2510.03119 [cs.RO]
(or arXiv:2510.03119v2 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2510.03119 Focus to learn more arXiv-issued DOI via DataCite
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.
Text integral sub licența deschisă a publicației · 277 cuvinte
Subiecte conexe
News Archive 2026
Quantum Computing Report · 25 iul. 2026

Skydio CEO Adam Bry on why Silicon Valley shouldn’t draw red lines for drone use
The Verge · 15 iun. 2026
AccelMPC: High-Rate, Low-Power FPGA-Accelerated Model Predictive Control for Tiny Drones
arXiv · 10 sept. 2026

Drone WMDs Don’t Need Any New Technology
LessWrong · 20 iul. 2026