# Are brain waves the next frontier for physical AI? A new era in robot training: Data generation via brainwave sensors. - **Source:** [TechCrunch](https://techcrunch.com) - **Published:** 2026-07-27 - **Topic:** [Data & AI](https://brifing.si/c/data-ai) - **Original article:** - **On Brifing:** https://brifing.si/s/0af1f6dc-1ff6-4a3d-9dd3-807d4761dce4 ## The new frontier of physical AI Encord measures brain waves of a pilot disassembling a Jenga tower in their California warehouse. This innovative approach aims to overcome real-world data scarcity in robotics training, moving beyond traditional methods. ## Brainwave-powered data generation Zander Labs' headset detects mental states like error and intent. The resulting dataset could enable more human-like decision making in robots. Currently in trial phase, this could revolutionize how we train physical AI models. ## Egocentric data collection Robotics companies now rely on two main data sources: 'egocentric' video from camera-equipped workers and remote-operated robots. Encord collects such data from factories worldwide to build comprehensive training sets. ## Emerging sensor technologies Encord is developing forearm sensors that detect muscle electrical signals. This creates 3D hand movement models to improve manipulation accuracy, addressing gaps in conventional video data collection methods. ## The economics of data generation Physical data production is far costlier than LLMs' web scraping. Encord's densely annotated datasets are 100x more valuable for specific tasks but cost 20x more to produce - a critical industry bottleneck that demands innovative solutions. ## Industrial transformation potential Brainwave data could revolutionize fields from warehouse automation to domestic robots. Encord's cross-industry visibility positions it to identify winning approaches as physical AI evolves beyond current limitations. ## Sources covering this story - https://techcrunch.com/2026/07/26/are-brain-waves-the-next-unlock-for-physical-ai/ — --- _Summary written by Brifing from the original reporting. Copyright in the original article belongs to its publisher; read the full piece at the link above._