State of the Field
Recent advancements in human-robot collaboration (HRC) are increasingly focused on enhancing real-time interaction and adaptability in dynamic environments. Researchers are developing probabilistic models for accurate human motion prediction, which are crucial for ensuring safety and effective collaboration. These models leverage Gaussian processes to provide reliable uncertainty estimates while maintaining computational efficiency, making them suitable for real-time applications. Additionally, new frameworks are emerging that integrate large language models to facilitate adaptive assembly processes, enabling robots to handle customized tasks without predefined instructions. This shift towards more interactive systems includes dual-mode planning that allows robots to actively engage with human partners, reducing communication costs and improving task execution efficiency. Furthermore, systems designed for bimanual teleoperation are demonstrating significant improvements in user experience and performance by accurately inferring human intentions. Collectively, these developments signal a move towards more intuitive, flexible, and efficient human-robot partnerships across various commercial applications, from manufacturing to service industries.
Papers
1–5 of 5Towards Scalable Probabilistic Human Motion Prediction with Gaussian Processes for Safe Human-Robot Collaboration
Accurate human motion prediction with well-calibrated uncertainty is critical for safe human-robot collaboration (HRC), where robots must anticipate and react to human movements in real time. We propo...
CoViLLM: An Adaptive Human-Robot Collaborative Assembly Framework Using Large Language Models for Manufacturing
With increasing demand for mass customization, traditional manufacturing robots that rely on rule-based operations lack the flexibility to accommodate customized or new product variants. Human-Robot C...
Uncertainty Mitigation and Intent Inference: A Dual-Mode Human-Machine Joint Planning System
Effective human-robot collaboration in open-world environments requires joint planning under uncertain conditions. However, existing approaches often treat humans as passive supervisors, preventing au...
SUBTA: A Framework for Supported User-Guided Bimanual Teleoperation in Structured Assembly
In human-robot collaboration, shared autonomy enhances human performance through precise, intuitive support. Effective robotic assistance requires accurately inferring human intentions and understandi...
Cognition to Control - Multi-Agent Learning for Human-Humanoid Collaborative Transport
Effective human-robot collaboration (HRC) requires translating high-level intent into contact-stable whole-body motion while continuously adapting to a human partner. Many vision-language-action (VLA)...