Figure's recent large-scale testing of its humanoid robot revealed a 56% success rate in domestic tasks like toy collection, towel folding, and bed-making across 30 homes. Performance significantly improved, jumping from 8% to 56%, when the robot was trained on extensive human demonstration data via Figure's Index app. However, the tests were limited in scope, involved specific conditions, and competitors like Tesla's Optimus are still uncommercialized, while iRobot has faced bankruptcy. AI
IMPACT Demonstrates the critical role of diverse human demonstration data in advancing humanoid robot capabilities for domestic tasks.
RANK_REASON The item details a large-scale test of a humanoid robot, including performance metrics and market context, which falls under research and development rather than a product release. [lever_c_demoted from research: ic=1 ai=1.0]
Read on Mastodon — fosstodon.org →
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →