I am an Academy Research Fellow in the Intelligent Robotics group led by Professor Ville Kyrki at Aalto University. My research is about socially aware autonomous systems: vehicles and robots that can read human social cues such as gaze, attention and intent, anticipate what people will do next, and communicate their own intentions clearly.
My fellowship is funded by the Research Council of Finland (2026–2030). In it I lead the project Learning Socially Aware Behaviors: Developing Autonomous Systems with Situational Awareness in Dynamic Environments. The project develops Socially Aware Perception (SA2S), a framework that combines camera, radar and lidar data with insights from human gaze and cognitive behavior to anticipate what people will do next. For example, it should recognise when a pedestrian is about to cross the street. SA2S also uses probabilistic reasoning to account for risk and uncertainty. The aim is autonomous systems that are safer, easier to understand and more human-centred.
PhD in Electrical Engineering and Computer Science, 2022
Gwangju Institute of Science and Technology (GIST)
MS in System Engineering, 2015
Pakistan Institute of Engineering and Applied Sciences (PIEAS)
BS in Electrical Engineering, 2013
Pakistan Institute of Engineering and Applied Sciences (PIEAS)
This work proposes a domain adaptation framework that employs a style transfer technique for transfer learning from visible spectrum images to thermal images. The framework uses a generative adversarial network (GAN) to transfer the low- level features from the visible spectrum domain to the thermal domain through style consistency.
This paper explores the novel application of lane marking detection using an event camera by designing a convolutional encoder followed by the attention-guided decoder. The spatial resolution of the encoded features is retained by a dense atrous spatial pyramid pooling (ASPP) block. The additive attention mechanism in the decoder improves performance for high dimensional input encoded features that promote lane localization and relieve postprocessing computation.
Journal Publications
Conference Publications