Lele Cao

University of Melbourne, Tsinghua University

Papers

6

Total Citations

73

H-Index

4

About

Lele Cao is a leading researcher at the intersection of robotics, embodied AI, and multi-modal perception, with a primary focus on tactile and audio-visual navigation. His pioneering work in robotic tactile recognition introduced the 3T-RTCN model (29 citations), which leverages randomized tiling convolutional networks and hierarchical fusion for efficient spatio-temporal feature extraction from tactile sensory data. He further advanced this field with an end-to-end ConvNet employing residual orthogonal tiling and pyramid convolution ensembles (14 citations), significantly improving object recognition accuracy. In embodied navigation, Cao has made substantial contributions to audio-visual and echo-enhanced systems, including his 2023 work on echo-enhanced visual navigation (17 citations) that addresses challenges in poor illumination, and his exploration of self-attention mechanisms for audio-visual fusion (2 citations). His research extends to collaborative multi-agent acoustics (8 citations), demonstrating the practical application of room impulse responses for environmental characterization. Through his innovative fusion strategies and deep learning architectures, Cao continues to push the boundaries of how robots perceive and interact with their environments, with his work collectively garnering over 70 citations and shaping the future of intelligent robotic systems.

Research Focus

Key Achievements

4
H-Index
6
Papers
73
Total Citations
12
Avg Citations/Paper
🏆 Most Cited Paper
Efficient Spatio-Temporal Tactile Object Recognition with Randomized Tiling Convolutional Networks in a Hierarchical Fusion Strategy
29 citations · 2016
📈 Most Prolific Year: 2016 (2 Papers)
🤝 Key Collaborators: 14
🏛 Institutions: University of Melbourne, Tsinghua University

Top Papers

  1. 1
  2. 2
  3. 3
  4. 4
  5. 5
  6. 6

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago