- MENet: Multi-Modal Mapping Enhancement Network for 3D Object Detection in Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems, 2024, 1-14 more…
- MENet: Multi-Modal Mapping Enhancement Network for 3D Object Detection in Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems 25 (8), 2024, 9397-9410 more…
- Modeling Grid Cell Distortions with a Grid Cell Calibration Mechanism. Cyborg and Bionic Systems, 2024 more…
- Optimizing Dynamic Balance in a Rat Robot Via the Lateral Flexion of a Soft Actuated Spine. IEEE International Conference on Robotics and Automation, 2024 more…
- An Energy-Efficient Lane-Keeping System Using 3D LiDAR Based on Spiking Neural Network. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), IEEE, 2023 more…
- Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), 2023 more…
- Toward Intelligent Sensing: Optimizing Lidar Beam Distribution for Autonomous Driving. IEEE Transactions on Intelligent Transportation Systems 24 (8), 2023, 8386-8392 more…
- Towards cognitive navigation: A biologically inspired calibration mechanism for the head direction cell network. Journal of Automation and Intelligence 2 (1), 2023, 31-41 more…
- Toward Neuromorphic Perception: Spike-driven Lane Segmentation for Autonomous Driving using LiDAR Sensor. IEEE 26th International Conference on Intelligent Transportation Systems, 2023 more…
- An Energy-Efficient Lane-Keeping System Using 3D LiDAR Based on Spiking Neural Network. 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2023), 2023 more…
- Learning from symmetry: Meta-reinforcement learning with symmetric data and language instructions. arXiv preprint, 2022 more…
- Learning from symmetry: Meta-reinforcement learning with symmetric data and language instructions. arXiv preprint, 2022 more…
- A Biologically-Inspired Global Localization System for Mobile Robots Using LiDAR Sensor. 2022 IEEE Intelligent Vehicles Symposium (IV), IEEE, 2022 more…
- A Biologically Inspired Simultaneous Localization and Mapping System Based on LiDAR Sensor. 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS 2022), 2022 more…
- A Biologically Inspired Simultaneous Localization and Mapping System Based on LiDAR Sensor. arXiv preprint arXiv:2109.12910, 2021 more…
- Toward Cognitive Navigation: Design and Implementation of a Biologically Inspired Head Direction Cell Network. IEEE Transactions on Neural Networks and Learning Systems, 2021 more…
- Fusion-based Feature Attention Gate Component for Vehicle Detection based on Event Camera. IEEE Sensors Journal, 2021, 1-1 more…
- A Real-Time Embedded Localization in Indoor Environment Using LiDAR Odometry. In: Communications in Computer and Information Science. Springer Singapore, 2018 more…
M.Eng. Genghang Zhuang
Technical University of Munich
Informatics 6 - Chair of Robotics, Artificial Intelligence and Real-time Systems (Prof. Knoll)
Postal address
Boltzmannstr. 3
85748 Garching b. München
Office hours: appointment by mail
Room: 5607.03.059
Curriculum Vitae
Genghang Zhuang is currently a doctoral student at Chair of Robotics, Artificial Intelligence and Real-time Systems, Department of Informatics, Technical University of Munich. He received his M.Eng degree in Software Engineering at Sun Yat-sen University, China, in 2019, and his B.Eng degree in Software Engineering at the same university in 2017.
His research interests include perception and planning in autonomous driving, especially with LiDAR sensors and biologically inspired methods.
| Oct. 2019 - Present | Research assistant, Ph.D. student at Informatics 6, Technical University of Munich |
| Sept. 2017 - June 2019 | M.Eng. at School of Computer Science and Engineering, Sun Yat-sen University, China |
| Aug. 2013 - June 2017 | B.Eng. at School of Computer Science and Engineering, Sun Yat-sen University, China |
Thesis Topics
This research explores the development of a brain-inspired mapping and localization algorithm for autonomous robots. Drawing inspiration from the spatial navigation system of mammalian brains, particularly grid cells, place cells, and head direction cells, the study aims to integrate these biological principles into a SLAM algorithm. The algorithm will leverage LiDAR sensors for enhanced accuracy and robustness, ultimately improving the robot's localization and mapping capabilities in various environments.
This research addresses the challenge of autonomous navigation for vehicles and robots, focusing on the use of LiDAR sensors for accurate environmental perception. While deep artificial neural networks (ANNs) are powerful for autonomous navigation, their computational demands limit deployment on power-constrained vehicles. The study proposes employing spiking neural networks, which mimic natural neural networks and can run efficiently on neuromorphic processors. The goal is to develop an end-to-end spiking neural network solution for autonomous navigation, integrating LiDAR sensor data.
This research tackles the intricate task of autonomous vehicle perception. Despite the accuracy of Light Detection And Ranging (LiDAR) sensors in providing a detailed environment point cloud, the computational demands of deep artificial neural networks (ANNs) hinder their deployment on power-constrained vehicles. The study proposes the use of biologically-inspired algorithms, specifically spiking neural networks (SNNs), known for mimicking natural behaviors. SNNs offer efficient computation on neuromorphic processors, making them suitable for autonomous perception problems. The research aims to develop an SNN solution for autonomous perception, with a focus on integrating LiDAR data.
If you are interested in one of the topics, please feel free to contact him.
Teaching
The practical courses delve into the field of autonomous robots, encompassing systems like self-driving vehicles and robotic arms. The courses address the complexities of autonomous robotics, exploring sensor technology, control systems, and action planning. Emphasizing biologically inspired computing, the courses aim to solve perception and navigation challenges using both conventional AI methods and biologically inspired approaches. Students will work in small groups, undertaking projects throughout the semester, focusing on applying models and methods to develop cognitive algorithms, particularly in the context of autonomous vehicle and robot.
Demos
• LiDAR based SLAM and Navigation
