Self-Predictive Representation for Autonomous UAV Object-Goal Navigation

Autonomous Unmanned Aerial Vehicles (UAVs) have revolutionized industries through their versatility with applications including aerial surveillance, search and rescue, agriculture, and delivery. Their autonomous capabilities offer unique advantages, such as operating in large open space environments. Reinforcement Learning (RL) empowers UAVs to learn intricate navigation policies, enabling them to optimize flight behavior autonomously. However, one of its main challenge is the inefficiency in using data sample to achieve a good policy. In object-goal navigation (OGN) settings, target recognition arises as an extra challenge. Most UAV-related approaches use relative or absolute coordinates to move from an initial position to a predefined location, rather than to find the target directly. This study addresses the data sample efficiency issue in solving a 3D OGN problem, in addition to, the formalization of the unknown target location setting as a Markov decision process. Experiments are conducted to analyze the interplay of different state representation learning (SRL) methods for perception with a model-free RL algorithm for planning in an autonomous navigation system. The main contribution of this study is the development of the perception module, featuring a novel self-predictive model named AmelPred. Empirical results demonstrate that its stochastic version, AmelPredSto, is the best-performing SRL model when combined with actor-critic RL algorithms. The obtained results show substantial improvement in RL algorithms' efficiency by using AmelPredSto in solving the OGN problem.

Bearing-Only Tracking and Circumnavigation of a Fast Time-Varied Velocity Target Utilising an LSTM

Bearing-only tracking, localisation, and circumnavigation is a problem in which a single or a group of agents attempts to track a target while circumnavigating it at a fixed distance using only bearing measurements. While previous studies have addressed scenarios involving stationary targets or those moving with an unknown constant velocity, the challenge of accurately tracking a target moving with a time-varying velocity remains open. This paper presents an approach utilising a Long Short-Term Memory (LSTM) based estimator for predicting the target's position and velocity. We also introduce a corresponding control strategy. When evaluated against previously proposed estimation and circumnavigation approaches, our approach demonstrates significantly lower control and estimation errors across various time-varying velocity scenarios. Additionally, we illustrate the effectiveness of the proposed method in tracking targets with a double integrator nonholonomic system dynamics that mimic real-world systems.