AI Robotics Researcher Intern (Dexterous Manipulation)

About the Position We are looking for an outstanding AI Robotics Research Intern to join the team at NIO. This role operates at the cutting edge of embodied AI and dexterous manipulation, with a specific focus on utilizing large-scale foundation models and human data-based learning to empower robots with physical world intelligence. As an intern, you will tackle the fundamental challenges of dexterous manipulation by harvesting human-object interaction data from diverse sources—ranging from unstructured web videos to high-fidelity human glove-collected data. Your work will involve translating these rich human insights into executable robotic behaviors, bridging the gap between human dexterity and machine execution. You will be responsible for deploying these policies on real hardware, to perform complex, contact-rich tasks in real-world environments

Project Scope

• Learning from Human Demonstrations: Develop and refine scalable frameworks for the transfer of human-object interaction skills to diverse robotic embodiments.
• Large-Scale Data Synthesis: Architect autonomous pipelines to process vast amounts of visual data and human glove-collected data, extracting the spatial and contact-rich information necessary for generalist robot training.
• Generative Embodied AI : Implement state-of-the-art generative architectures to synthesize physically grounded, high-fidelity trajectories based on human reference motions.
• Unified Policy Training: Explore cross-embodiment representations that enable joint training on human and robot data to improve generalization in unstructured environments.
• Sim-to-Real Deployment: Research and optimize distillation and retargeting techniques to bridge the gap between simulation-trained policies and physical robotic deployment.
• Semantic Scene Understanding: Utilize vision-language foundation models to autonomously segment skills and extract task-relevant parameters from complex human activities.

Deliverables (End of Internship)

…