Dugki Min

Bhaskar Prasad Rimal, Idris E. Putro, Agus Budiyono et al.

UAV control system is a huge and complex system, and to design and test a UAV control system is time-cost and money-cost. This paper considered the simulation of identification of a nonlinear system dynamics using artificial neural networks approach. This experiment develops a neural network model of the plant that we want to control. In the control design stage, experiment uses the neural network plant model to design (or train) the controller. We use Matlab to train the network and simulate the behavior. This chapter provides the mathematical overview of MRC technique and neural network architecture to simulate nonlinear identification of UAV systems. MRC provides a direct and effective method to control a complex system without an equation-driven model. NN approach provides a good framework to implement MEC by identifying complicated models and training a controller for it.

Seunghyeop Nam, Tuan Anh Nguyen, Eunmi Choi et al.

Autonomous robot exploration in large-scale or cluttered environments remains a central challenge in intelligent vehicle applications, where partial or absent prior maps constrain reliable navigation. This paper introduces FH-DRL, a novel framework that integrates a customizable heuristic function for frontier detection with a Twin Delayed DDPG (TD3) agent for continuous, high-speed local navigation. The proposed heuristic relies on an exponential-hyperbolic distance score, which balances immediate proximity against long-range exploration gains, and an occupancy-based stochastic measure, accounting for environmental openness and obstacle densities in real time. By ranking frontiers using these adaptive metrics, FH-DRL targets highly informative yet tractable waypoints, thereby minimizing redundant paths and total exploration time. We thoroughly evaluate FH-DRL across multiple simulated and real-world scenarios, demonstrating clear improvements in travel distance and completion time over frontier-only or purely DRL-based exploration. In structured corridor layouts and maze-like topologies, our architecture consistently outperforms standard methods such as Nearest Frontier, Cognet Frontier Exploration, and Goal Driven Autonomous Exploration. Real-world tests with a Turtlebot3 platform further confirm robust adaptation to previously unseen or cluttered indoor spaces. The results highlight FH-DRL as an efficient and generalizable approach for frontier-based exploration in large or partially known environments, offering a promising direction for various autonomous driving, industrial, and service robotics tasks.

Hojoon Lee, Hyeonseo Cho, Hyunseung Kim et al.

This study investigates the loss of generalization ability in neural networks, revisiting warm-starting experiments from Ash & Adams. Our empirical analysis reveals that common methods designed to enhance plasticity by maintaining trainability provide limited benefits to generalization. While reinitializing the network can be effective, it also risks losing valuable prior knowledge. To this end, we introduce the Hare & Tortoise, inspired by the brain's complementary learning system. Hare & Tortoise consists of two components: the Hare network, which rapidly adapts to new information analogously to the hippocampus, and the Tortoise network, which gradually integrates knowledge akin to the neocortex. By periodically reinitializing the Hare network to the Tortoise's weights, our method preserves plasticity while retaining general knowledge. Hare & Tortoise can effectively maintain the network's ability to generalize, which improves advanced reinforcement learning algorithms on the Atari-100k benchmark. The code is available at https://github.com/dojeon-ai/hare-tortoise.

Junghyun Park, Tuan Anh Nguyen, Dugki Min

Real world deployments often expose modern object recognition models to domain shifts that precipitate a severe drop in accuracy. Such shifts encompass (i) variations in low level image statistics, (ii) changes in object pose and viewpoint, (iii) partial occlusion, and (iv) visual confusion across adjacent classes. To mitigate this degradation, we introduce the Re-Thinking Vision Language Model (RT-VLM) framework. The foundation of this framework is a unique synthetic dataset generation pipeline that produces images annotated with "4-Clues": precise bounding boxes, class names, detailed object-level captions, and a comprehensive context-level caption for the entire scene. We then perform parameter efficient supervised tuning of Llama 3.2 11B Vision Instruct on this resource. At inference time, a two stage Re-Thinking scheme is executed: the model first emits its own four clues, then re examines these responses as evidence and iteratively corrects them. Across robustness benchmarks that isolate individual domain shifts, RT-VLM consistently surpasses strong baselines. These findings indicate that the integration of structured multimodal evidence with an explicit self critique loop constitutes a promising route toward reliable and transferable visual understanding.