MFI 2022 - Workshops

If you are interested in contributing to the below workshops, please reach out to the proposers directly or email 

WS1: Neuromorphic Event Sensor Fusion Algorithms and their Applications

Contact Proposers:

Min Liu (Postdoc, University of Zurich and ETH Zurich)

Tobi Delbruck (Professor, University of Zurich and ETH Zurich)


Event-based sensors such as the event-based silicon retinas and cochleas have recently attracted attention from the robotics, IoT, and TinyML communities because DVS has the potential to improve current visual odometry and mapping thanks to its low latency, high dynamic range, and high time resolution, and DAS can provide always-on activity-driven audio inference at low average power consumption. It is necessary to have a wider discussion on this topic to facilitate its use in robotics, human interaction, and IoT. Therefore, we propose to organize the first workshop on event-based sensor fusion for academia and industry.

Dedicated workshop website:


WS2: OPV2V: Open Large-scale Multi-agent Perception Challenge

Contact Proposers:

Jiaqi Ma (Associate Professor, UCLA)

Xin Xia (Assistant Project Scientist, UCLAu)


Single-vehicle perception systems tend to suffer from occlusion and sparse sensor observation at a far distance, which can potentially lead to failure to detect objects and cause catastrophic consequences such as collisions. By utilizing Vehicle-to-Everything (V2X) communication technology, nearby vehicles can share visual information (e.g., raw sensory information, deep learning features, and detection outputs) to obtain multiple viewpoints of the same scene, leading to more accurate object detection and thus, better complete scene understanding. This challenge aims to spotlight the problems of efficient algorithm design for visual information fusion from different vehicles to perform cooperative 3D object detection.


WS3: Robust Sensing and Perception with Deep Learning

Contact Proposers:

Wei Tian (Assistant Professor, Tongji University,


The main objective of this workshop is to present the new researches related to the robust environmental sensing and perception technique, involving the analysis of specified problems, the insights into perception modelling and the opportunities with the development of new sensor technology.



WS4: The First Workshop on Safe Reinforcement Learning Theory and its Applications

Contact Proposers:

Shangding Gu, (Technical University of Munich,


Developing reinforcement learning (RL) algorithms that satisfy safety constraints is becoming increasingly important in real-world applications. How to ensure safety during RL applications is a challenging problem, which has received substantial attention in recent years. A Safe RL problem can be seen as a Constrained Markov Decision Process (CMDP) problem, which has been widely adopted in the field of Safe RL. There are lots of methods and algorithms that have been proposed and developed for Safe RL based on CMDP optimization. It’s necessary to organize “MFI 2022 Workshop on Safe Reinforcement Learning Theory and its Applications” and discuss how to address safe RL problems with researchers from academics and industries. Moreover, the workshop is close to the Human-Machine Systems.