Fasih Munir Malik

The future of industrial automation depends on the ability of human operators to effectively manage fleets of increasingly autonomous machines. This research aims to develop a novel Multimodal Human-Machine Interface (HMI) ecosystem that empowers operators to supervise and control multiple mobile machines safely and efficiently. Traditionally, fleet operations required a large workforce, but advancements in machine autonomy are driving a shift towards single-operator control of multi-machine systems.
This study will address critical aspects such as cognitive workload assessment, task allocation strategies, and adaptive autonomy. Utilizing established techniques like NASA-TLX, the research will identify optimal workload thresholds and design systems for dynamically allocating tasks between humans and machines. Adaptive shared control models will be explored to ensure seamless transitions between manual and autonomous operation, with autonomy levels adjusted in real-time based on workload and environmental conditions.
The proposed HMI will integrate multimodal interfaces—including visual, auditory, and haptic feedback—to enhance situational awareness and reduce cognitive load. Operator training will focus on developing skills in multitasking, system monitoring, and human-machine collaboration. The research hypothesizes that such an interface, leveraging technologies like computer vision and AI, will significantly improve operational efficiency and safety. This work is expected to yield a prototype HMI framework, driving innovation across industries such as construction, mining, and logistics.