Could a robot run for a flight without spilling its coffee? I started thinking about this during my own airport sprint, coffee in hand. For a humanoid, 6 senses are working together at all times: - Sight: What can it see? - Depth: How far away is the obstacle? - Balance: Where is its body, and is it balanced? - Force: How much force is it applying? - Tactile: Is something slipping at the contact surface? - Audio: What can it hear? New Core Matter @CoreMatter_ field guide walks through sight, depth, balance and position, force, touch, and hearing. Including each supply chain and deployment failure modes. The guide also looks at @Waymo's camera, lidar and radar approach and @Tesla's camera-based Tesla Vision.

Inside tactile robotics w/ Professor Shan Luo, King's College London Robot skin changes. Models must adapt. “But hardware still matters a lot.” Luo leads the Robot Perception Lab. We discuss Unilever's material-assessment questions, Ocado's delicate-object handling, and the data behind a robot's sense of touch. GenForce studies transferring force-prediction knowledge across tactile sensors. His ViTacGen example concerns object pushing: learning uses physical touch, while deployment in that task can use vision. We cover: › Material assessment and contact force › Cross-sensor learning with GenForce › Vision-to-touch generation for object pushing › What changes when robot skin is replaced? › Task-specific finger and sensor design › Unilever, Ocado and open tactile datasets Chapters 00:00 Cold open: what happens when robot skin changes? 00:29 Why Shan Luo chose tactile sensing 02:04 Scaling tactile data and simulation 03:40 The interface between different sensors 05:04 Material assessment, cleaning and insertion 09:18 Vision, contact and the last mile 11:54 Manipulating transparent objects 14:29 GenForce: transferring force-prediction knowledge 17:59 Hardware, shared datasets and standards 21:43 ViTacGen: learning from touch, deploying with vision 25:42 How tactile sensor skin wears 28:43 Replacement skin and model calibration 30:49 Manufacturing cost and consistency 32:38 TacDiff: designing the finger and policy together 36:47 Industrial research with Unilever and Ocado 40:01 ViTac workshop and open tactile data 45:11 A startup question and a surprise announcement 49:43 What warehouse robots could feel in 2031

I’ll be at IROS this week and look forward to connecting with researchers and operators building dexterous hands, autonomous factories, world models. Core Matter @corematter_ is co-hosting Robotics Research Night with Saturday Robotics @saturdayrobotic on Monday 9/28. Come join us for an evening of research discussions. Big thanks to our sponsors @FAIRplus_sz and Daimon Robotics. Come join us! Sign up here: luma.com/tzbw7n61 == @junfanzhu98 @aurorafeng_01