Welcome to the Robotic Computing and Chip Lab (RLC-Lab)!

About RLC-Lab

The Robotic Computing and Chip Lab (RLC-Lab) is a research laboratory dedicated to advancing the frontiers of robotic computing and chip design. Our lab focuses on developing innovative computing architectures and intelligent systems that bridge the gap between robotics and computational efficiency. We work on autonomous machines, an exciting area that may reform the way we live in the future. We hope to build autonomous machines that are more intelligent, more efficient and more reliable.

RLC-Lab is part of the Research Center for Intelligent Computing Systems (CICS) at the Institute of Computing Technology, Chinese Academy of Sciences (ICT, CAS). This affiliation provides us with access to world-class research facilities and collaboration opportunities within the broader academic community.

Research Areas

Our research encompasses several key areas:

Benchmarking Robotic Applications

One of the key factors for advancing research in robotic computing within our domain is the establishment of faithful benchmarking, which remains a significant challenge. The complexity of robotic systems necessitates benchmarking workloads that encompass algorithms from navigation, planning, and perception. Additionally, a robust benchmark must capture not only the individual algorithms but also their interconnections, primarily facilitated through ROS. Currently, we are actively working on several related projects to address these challenges.

• A real embodied AI robot system and corresponding workload characterization
• An open reference, multi-node benchmarking suite that is used to evaluate robotics computing performance
• Workload characterization of real-time systems on advanced processors
• Workload characterization for ROS2

Efficient Embodied AI Systems

We believe robots will have the ability of thinking. The goal of this direction is to enable robots to accomplish long and complex tasks and finish it in real time. The fundamental blocks here are in two folds. First, although large language models have shown ability to accomplish long horizon tasks, the gap between the output of language models and real physical world are huge. Second, the evolution of huge LLMs makes it impossible for the robots to finish its decision making chain in real time.

• Accelerator design for vision language action models
• Humanoid robot control
• Multi-chiplet CPU design

Reliability

Our research focuses on reliability, which we believe is particularly crucial in a world increasingly populated by robots. Ensuring reliability involves making software robust against various attacks and hardware resilient to different hazards.

• Reliability for Embodied AI System
• Software-Hardware Co-Design for Fault Tolerance in Wafer-Scale Chips

Our Mission

We strive to push the boundaries of what’s possible in robotic computing through innovative research, cutting-edge technology development, and collaborative partnerships. Our goal is to contribute to the advancement of intelligent computing systems that can enhance robotic capabilities and drive technological innovation.

Join Us

We welcome collaborations, research partnerships, and talented individuals who share our passion for advancing robotic computing and chip design. Whether you’re a researcher, student, or industry partner, we’d love to hear from you.

For more information about our research, publications, and team members, please explore the other sections of our website.