On June 25, 2025, Lunar Lab member Lingjun Zhao presented his research on GaussianFormer3D: Multi-Modal Gaussian-based Semantic Occupancy Prediction with 3D Deformable Attention in the workshop on Gaussian Representations for Robot Autonomy: Challenges and Opportunities at Robotics: Science and Systems (RSS) 2025. The work explores Gaussian-based scene representations of multi-modal data for semantic occupancy prediction, advancing efficient robot perception and autonomy.
From June 4-6, 2025, Lunar Lab members, Sizhe Wei, Lingjun Zhao, and Lu Gan attended the 7th Annual Learning for Dynamics & Control Conference held at the University of Michigan, Ann Arbor. The team presented their work on Morphological-Symmetry-Equivariant Heterogeneous Graph Neural Networks for Robotic Dynamics Learning and participated in a tour of the Michigan Robotics Lab at the Ford Robotics Building. It was also a pleasure to reconnect with Lu’s former lab members during the visit!
From May 19 to 23, 2025, the entire Lunar Lab attended the 2025 IEEE International Conference on Robotics and Automation (ICRA), the flagship conference of the IEEE Robotics and Automation Society (RAS), held in Atlanta, Georgia. Lab members organized an workshop, delivered workshop keynotes, oral and poster presentations, and participated in various professional and social events, including the Doctoral Consortium, RAS Technical Committee lunch, RAS Editorial Board dinner, and the Georgia Tech IRIM party. Several lab members also supported the conference as volunteers!
ICRA 2025 was an exciting and rewarding experience for the entire Lunar Lab. From presenting our research to engaging in insightful discussions and meaningful community events, the conference offered valuable opportunities to share our work, learn from others, exchange ideas, connect and contribute to the broader robotics community. We look forward to reconnecting with fellow researchers and friends at future conferences!
On April 8 2025, Lunar Lab hosted a Robotics Open House for local K–12 students and their families, aiming to inspire young minds by showcasing innovative robotics research and engaging them through interactive robot demonstrations.
We were delighted to welcome a local family of robotics enthusiasts as our first visitors. Lu and Sandilya introduced how our drones use onboard sensors such as cameras and computer vision technologies to localize themselves and perceive the physical world. Daniel also had an engaging discussion with them about the potential of legged robots to transform mobility and logistics in challenging environments. The family interacted enthusiastically with our robot demonstrations and expressed strong interest in the technologies we are developing.
We were also thrilled to host a local FIRST Robotics team and their dedicated mentor, Ms. Yang. The kids were excited to discover that Daniel, one of our lab members who led the quadrupedal robot demonstration, is an alumnus of the FIRST Robotics Competition (from 2013 to 2017). This shared connection sparked meaningful conversations about the journey from high school robotics to cutting-edge research.
Throughout the visit, attendees interacted with a range of robotic platforms, including our quadruped robot, wheeled robot, and drones. They learned about the underlying core technologies such as computer vision, machine learning, and autonomous navigation, while also being inspired by the transformative potential of robotics in transportation, elder care, agriculture, and space exploration. The live demonstrations of various platforms provided a hands-on understanding of how robots perceive and interact with both humans and their environment.
We extend our sincere thanks to all the visitors for their enthusiasm and curiosity, and to the organizers at IRIM for their support in making this vibrant outreach event a big success during National Robotics Week. Events like these underscore the importance of outreach in inspiring the next generation of engineers and scientists. By opening our doors and sharing the exciting world of robotics, we hope to spark lasting interest in STEM and empower young minds to imagine, explore, and innovate. We look forward to continuing our engagement with the community through future events and educational initiatives.
Special thanks to our lab members—Daniel, Sandilya, Sizhe, Lingjun, and Ziwon—for their support with the live demonstrations and presentation slides. Photo credit: Sizhe Wei.
