gemini-robotics-er-1-6-37894a9c·3 events·first seen Aliases: Gemini Robotics-ER 1.6, Gemini Robotics-ER, Gemini Robotics-ER 1.5
Researchers at Stanford and UC Berkeley developed RoboReward, a family of 4B and 8B vision-language reward models designed to provide reward signals for robot reinforcement learning across diverse robot types and tasks. The team built a novel dataset by augmenting successful robot demonstrations with synthetically generated failure examples using GPT-5 mini and Qwen3-4B, then fine-tuned Qwen3-VL models to predict task progress scores. RoboReward 8B outperformed GPT-5, GPT-5 mini, and Gemini Robotics-ER 1.5 on the new RoboRewardBench evaluation, and in real-world robot trials substantially exceeded prior reward model baselines while still falling short of human-assigned rewards. The authors also release RoboRewardBench as a community benchmark for reward model evaluation.
Google DeepMind has announced Gemini Robotics and Gemini Robotics-ER, two AI models purpose-built for robotic systems to perceive, reason about, and act within physical environments. The release extends the Gemini model family into embodied AI and robotics applications. Gemini Robotics-ER appears to target enhanced reasoning capabilities for robotic control. This marks a significant step by DeepMind toward deploying frontier multimodal models in physical-world settings.
DeepMind has released Gemini Robotics-ER 1.6, an updated embodied reasoning model targeting spatial reasoning and multi-view understanding for autonomous robotics applications. The release represents an incremental update to the Gemini Robotics-ER line, focused on improving real-world task performance. The announcement comes from DeepMind's official blog, indicating a production-grade capability update rather than a research preview.