Ioannis Kansizoglou

About

Ioannis Kansizoglou is a researcher whose work sits at the dynamic intersection of human-robot interaction, affective computing, and neuromorphic intelligence. His research spans emotion recognition, assistive robotics, reinforcement learning, and autonomous navigation, with a particular emphasis on building systems that are both computationally powerful and energy-efficient. Kansizoglou's most influential contribution, "An Active Learning Paradigm for Online Audio-Visual Emotion Recognition" (2019, 114 citations), pioneered a multi-modal framework for real-time emotion detection, significantly advancing how robots perceive and respond to human affective states. Building on this, his work on continuous emotion recognition through recurrent neural networks (2022, 40 citations) demonstrated how sustained emotional modeling can inform long-term personality assessment — a vital capability for companion and assistive robots. A recurring theme in his research is the application of spiking neural networks to robotics, producing energy-efficient solutions for robotic arm manipulation and reinforcement learning-based planning (collectively amassing nearly 50 citations). His survey on assistive robotics for elderly care and his work toward Warehouse 5.0 further reveal a commitment to translating cutting-edge AI into real-world human-centered applications. Kansizoglou represents a forward-thinking voice in making intelligent robotics both socially responsive and computationally sustainable.

Research Focus

Key Achievements

Top Papers

1. 1
   An Active Learning Paradigm for Online Audio-Visual Emotion Recognition

   114 citations · 2019
2. 2
   Continuous Emotion Recognition for Long-Term Behavior Modeling through Recurrent Neural Networks

   40 citations · 2022
3. 3
   A Hybrid Reinforcement Learning Approach With a Spiking Actor Network for Efficient Robotic Arm Target Reaching

   31 citations · 2023
4. 4
   A Survey on Technical Challenges of Assistive Robotics for Elder People in Domestic Environments: The ASPiDA Concept

   31 citations · 2023
5. 5
   A Hybrid Spiking Neural Network Reinforcement Learning Agent for Energy-Efficient Object Manipulation

   18 citations · 2023
6. 6
   Fall detection paradigm for embedded devices based on YOLOv8

   11 citations · 2023
7. 7
   Towards Warehouse 5.0: A Framework of Human-Centered Technologies

   7 citations · 2024
8. 8
   A Framework for Active Vision-Based Robot Planning using Spiking Neural Networks

   7 citations · 2022
9. 9
   Learning Long-Term Behavior through Continuous Emotion Estimation

   6 citations · 2021
10. 10
    Visual Place Recognition in Changing Environments with Sequence Representations on the Distance-Space Domain

    5 citations · 2023

Key Collaborators

Contact & Links