Energy consumption optimization is crucial for the navigation of Unmanned Aerial Vehicles (UAV), as they operate solely on battery power and have limited access to charging stations. In this paper, a novel deep reinforcement learning-based architecture has been proposed for planning energy-efficient and collision-free paths for a quadrotor UAV. The proposed method uses a unique combination of remaining flight distance and local knowledge of energy expenditure to compute an optimized route. An information graph is used to map the environment in three dimensions and obstacles inside a pre-determined neighbourhood of the UAV are removed to obtain a local as well as collisionfree reachable space. Attention-based neural network forms the key element of the proposed reinforcement learning mechanism, that trains the UAV to autonomously generate the optimized route using partial knowledge of the environment, following the trajectories from which, the UAV is driven by the trajectory tracking controller.

No abstract

Pursuit evasion is an important category of mobile robotics application related to surveillance, spying and gathering ambient information. This paper presents a novel optimal approach to evasion planning, considering physical limitations of the environment and the evader. The results show that the proposed formulation is applicable irrespective of the number of pursuing agents and the relative velocities of the pursuers and the evader, contrary to the traditional requirement that evasion strategies need to be configured according to situation-dependent cases. The proposed policy is generic and can be implemented in real-time by iterative optimization using model predictive controllers, the objective being avoidance of capture or at the least, maximizing the capture time.