Obstacle avoidance and trajectory optimisation for an autonomous vessel utilising MILP path planning, computer vision based perception and feedback control

In this study, we investigated autonomous vessel obstacle avoidance using advanced techniques within the Guidance, Navigation, and Control (GNC) framework. We propose a Mixed Integer Linear Programming (MILP) based Guidance system for robust path planning avoiding static and dynamic obstacles. For Navigation, we suggest a multi-modal neural...

Advancing deep learning-based detection of floating litter using a novel open dataset

Supervised Deep Learning (DL) methods have shown promise in monitoring the floating litter in rivers and urban canals but further advancements are hard to obtain due to the limited availability of relevant labeled data. To address this challenge, researchers often utilize techniques such as transfer learning (TL) and data augmentation (DA)....

Deep Reinforcement Learning for Goal-directed Visual Navigation

Safe navigation in a cluttered environment is a key capability for the autonomous operation of Micro Aerial Vehicles (MAVs). This work explores a (deep) Reinforcement Learning (RL) based approach for monocular vision based obstacle avoidance and goal directed navigation for MAVs in cluttered environments. We investigated this problem in the...

Envision: enabling vision for visually impaired

Envision began as an attempt to increase independence for people with visual impairment. During the course of the project, through a very participatory design approach, a deep understanding of the challenges faced by visually impaired people was obtained. A technology exploration in search for potential solutions led to the discovery of the...