Autonomous systems like unmanned aircraft systems are touted as front-runners in
terms of efficiency and agility in challenging operations like emergency response. Ability of autonomous agents in unmanned systems to avoid collision with dynamic obstacles while navigating through an obstacle-cluttered environment is difficult and thus is
critical for success in any mission. This problem becomes challenging in unstructured
environments due to uncertainties in different aspects like obstacles’ motion, sensing
and occluded regions. To this end, a higher-order velocity-obstacle-based novel motion
planner is presented in this thesis in a probabilistic set-up for smooth (second-order continuous), collision-free trajectory planning of the agent with acceleration constraints in
uncertain and unstructured environments. The developed algorithm for the agent also
utilizes a Gaussian Process (GP)-based anticipation for the future environment. Effectiveness of the developed algorithm for safe, collision-free, and second-order continuous navigation of the agent is investigated in simulation studies in two different kinds
of environments, one with known trajectories of obstacles and the other with unknown
curved trajectories of obstacles. Extensive simulation studies are performed in the presence of dynamic obstacles to elucidate the performance of the proposed algorithm on
four crucial parameters - mission time, computational time, minimum obstacle distance
and overall control effort under varied obstacle densities. With satisfactory performance
in all these aspects in a simulated setup, the developed algorithm possesses strong potential for real-time implementation in realistic systems.
The success rate of the proposed algorithm depends on the accuracy of prediction
of future states of the obstacles by the GP algorithm. However, GP-based predictions
are usually not interaction-aware and therefore, cannot take in account the contextual
cues in the environment like the presence of static physical obstacles, social conventions, etc. in its forecasting. Social Forces-based existing interaction-aware methods
ii
consider generic social interactions like human-human interaction, human-dynamic obstacle interaction, etc. However, their effectiveness gets limited when the complexity
of interactions increases (with human-static obstacles, etc.). To this end, a statistical
behavioural model, termed Social Gaussian Process (SGP) model, which combines the
Social Force model (to capture the contextual cues and social conventions of movement
in the presence of dynamic, static obstacles) with the Gaussian Process (to reliably learn
complex interactions using the past data) in a Bayesian framework is subsequently presented in this thesis. Predictions for the agents is made further amended by embedding
the consideration of sensing and dynamic feasibility in the SGP formulation. Simulation results are presented to justify the betterment of performance of SGP than that of
the GP-based one.