SenseTime co-founder’s ACE Robotics releases model for robot spatial perception

ACE Robotics, founded by SenseTime co-founder Xiaogang Wang, released its ACE-Brain-0.6 embodied AI model on October 19, built by supervised fine-tuning Qwen3.5-9B on roughly 1 million spatial-grounding samples to identify objects, locate them in images and determine where a robot can interact with them. ACE Robotics reported that ACE-Brain-0.6 beat GPT-6 Astra on six of eight grounding benchmarks, averaging 74.53 across seven public benchmarks and 94.13 on RobotGrounding versus Astra's 73.68 and 91.10.

ACE Robotics, founded by SenseTime co-founder Xiaogang Wang, released its ACE-Brain-0.6 embodied AI model on October 19. Built through supervised fine-tuning of Qwen3.5-9B, the model focuses on identifying objects, locating them in images and determining where a robot can interact with them. The company said it trained the model using approximately 1 million spatial-grounding samples. In its reported evaluations, ACE-Brain-0.6 outperformed GPT-6 Astra on six of eight grounding benchmarks. It scored an average of 74.53 across seven public benchmarks and 94.13 on RobotGrounding, an evaluation based on real robot scenarios, compared with Astra’s 73.68 and 91.10, respectively. Pandaily https://pandaily.com/ace-robotics-ace-brain-0-6-9b-visual-grounding-spatial-supervision-qwen3-5-gpt-6-astra