Geesara Kulathunga

Mohamad Al Mdfaa, Raghad Salameh, Geesara Kulathunga et al.

In robotics and computer vision, semantic mapping remains a critical challenge for machines to comprehend complex environments. Traditional panoptic mapping approaches are constrained by fixed labels, limiting their ability to handle novel objects. We present Unified Promptable Panoptic Mapping (UPPM), which leverages foundation models for dynamic labeling without additional training. UPPM is evaluated across three comprehensive levels: Segmentation-to-Map, Map-to-Map, and Segmentation-to-Segmentation. Results demonstrate UPPM attains exceptional geometry reconstruction accuracy (0.61cm on the Flat dataset), the highest panoptic quality (0.414), and better performance compared to state-of-the-art segmentation methods. Furthermore, ablation studies validate the contributions of unified semantics, custom NMS, and blurry frame filtering, with the custom NMS improving the completion ratio by 8.27% on the Flat dataset. UPPM demonstrates effective scene reconstruction with rich semantic labeling across diverse datasets.

Geesara Kulathunga, Hany Hamed, Dmitry Devitt et al.

The goal of this paper is to develop a continuous optimization-based refinement of the reference trajectory to 'push it out' of the obstacle-occupied space in the global phase for Multi-rotor Aerial Vehicles in unknown environments. Our proposed approach comprises two planners: a global planner and a local planner. The global planner refines the initial reference trajectory when the trajectory goes either through an obstacle or near an obstacle and lets the local planner calculate a near-optimal control policy. The global planner comprises two convex programming approaches: the first one helps to refine the reference trajectory, and the second one helps to recover the reference trajectory if the first approach fails to refine. The global planner mainly focuses on real-time performance and obstacles avoidance, whereas the proposed formulation of the constrained nonlinear model predictive control-based local planner ensures safety, dynamic feasibility, and the reference trajectory tracking accuracy for low-speed maneuvers, provided that local and global planners have mean computation times 0.06s (15Hz) and 0.05s (20Hz), respectively, on an NVIDIA Jetson Xavier NX computer. The results of our experiment confirmed that, in cluttered environments, the proposed approach outperformed three other approaches: sampling-based pathfinding followed by trajectory generation, a local planner, and graph-based pathfinding followed by trajectory generation.

Geesara Kulathunga

Optimal motion planning involves obstacles avoidance where path planning is the key to success in optimal motion planning. Due to the computational demands, most of the path planning algorithms can not be employed for real-time based applications. Model-based reinforcement learning approaches for path planning have received certain success in the recent past. Yet, most of such approaches do not have deterministic output due to the randomness. We analyzed several types of reinforcement learning-based approaches for path planning. One of them is a deterministic tree-based approach and other two approaches are based on Q-learning and approximate policy gradient, respectively. We tested preceding approaches on two different simulators, each of which consists of a set of random obstacles that can be changed or moved dynamically. After analysing the result and computation time, we concluded that the deterministic tree search approach provides highly stable result. However, the computational time is considerably higher than the other two approaches. Finally, the comparative results are provided in terms of accuracy and computational time as evidence.

Geesara Kulathunga, Dmitry Devitt, Roman Fedorenko et al.

We explore path planning followed by kinodynamic smoothing while ensuring the vehicle dynamics feasibility for MAVs. We have chosen a geometrically based motion planning technique \textquotedblleft RRT*\textquotedblright\; for this purpose. In the proposed technique, we modified original RRT* introducing an adaptive search space and a steering function which help to increase the consistency of the planner. Moreover, we propose multiple RRT* which generates a set of desired paths, provided that the optimal path is selected among them. Then, apply kinodynamic smoothing, which will result in dynamically feasible as well as obstacle-free path. Thereafter, a b spline-based trajectory is generated to maneuver vehicle autonomously in unknown environments. Finally, we have tested the proposed technique in various simulated environments.

Geesara Kulathunga, Roman Fedorenko, Sergey Kopylov et al.

Real-time long-range local planning is a challenging task, especially in the presence of dynamics obstacles. We propose a complete system which is capable of performing the local replanning in real-time. Desired trajectory is needed in the system initialization phase; system starts initializing sub-components of the system including point cloud processor, trajectory estimator and planner. Afterwards, the multi-rotary aerial vehicle starts moving on the given trajectory. When it detects obstacles, it replans the trajectory from the current pose to pre-defined distance incorporating the desired trajectory. Point cloud processor is employed to identify the closest obstacles around the vehicle. For replanning, Rapidly-exploring Random Trees (RRT*) is used with two modifications which allow planning the trajectory in milliseconds scales. Once we replanned the desired path, velocity components(x,y and z) and yaw rate are calculated. Those values are sent to the controller at a constant frequency to maneuver the vehicle autonomously. Finally, we have evaluated each of the components separately and tested the complete system in the simulated and real environments.