Research Group for Neuromorphic Computing
Introduction
The Research Group for Neuromorphic Computing develops advanced neural-network based algorithms, software libraries, and systems with the new generation of computing chips – brain-inspired neuromorphic sensing and computing hardware. We focus on perception, motion planning, and control for robotic actuators with applications in life sciences: healthcare, agriculture, food processing, and smart environments. We follow a human-centered design approach to develop new generation of physical AI systems that are power-efficient, adaptive, and safe.
Expertise
- Neuromorphic computing hardware and algorithms
- Event-based vision
- Robotics: Motion planning, control, SLAM
- Efficient machine learning and AI
- Dynamical systems, cognitive architectures
Areas of application
- Assistive robotics in healthcare, agriculture, food processing, smart environments
- Machine vision in healthcare, agriculture, food processing, smart environments
- Continual learning and adaptive systems
- Robot safety, human-robot interaction
Collaborations and partners
Engagement in teaching
Our research group includes teaching engagements at BSc and MSc level as well as in continuing education.
Our Team
-
ZHAW School of Life Sciences and Facility Management
FS Cognitive Computing in Life Sciences
-
ZHAW School of Life Sciences and Facility Management
FG Neuromorphic Computing Group
Schloss 1
8820 Wädenswil -
ZHAW School of Life Sciences and Facility Management
FG Neuromorphic Computing Group
Current projects
-
Reinforcement Learning Analysis Framework
The aim of this project is to implement a framework that facilitates the development of RL solutions for real-world applications. This is necessary since the academic literature usually focuses on specific algorithms and approaches differ widely for different regions in the highly complex RL problem space. ...
-
Optimizing plant health in indoor farming using reinforcement learning
The research question we tackle in this project is "How can we automatically optimize the growth path of indoor-farming plants?". To achieve this goal, we develop new algorithms to measure plant health and growth. We then evaluate reinforcement learning based approaches to optimize these metrics. ...