Raul Steinmetz

Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz et al.

Kolmogorov-Arnold Networks (KANs) have shown potential as an alternative to Multi-Layer Perceptrons (MLPs) in neural networks, providing universal function approximation with fewer parameters and reduced memory usage. In this paper, we explore the use of KANs as function approximators within the Proximal Policy Optimization (PPO) algorithm. We evaluate this approach by comparing its performance to the original MLP-based PPO using the DeepMind Control Proprio Robotics benchmark. Our results indicate that the KAN-based reinforcement learning algorithm can achieve comparable performance to its MLP-based counterpart, often with fewer parameters. These findings suggest that KANs may offer a more efficient option for reinforcement learning models.

Linda Dotto de Moraes, Victor Augusto Kich, Alisson Henrique Kolling et al.

In this work, we present two Deep Reinforcement Learning (Deep-RL) approaches to enhance the problem of mapless navigation for a terrestrial mobile robot. Our methodology focus on comparing a Deep-RL technique based on the Deep Q-Network (DQN) algorithm with a second one based on the Double Deep Q-Network (DDQN) algorithm. We use 24 laser measurement samples and the relative position and angle of the agent to the target as information for our agents, which provide the actions as velocities for our robot. By using a low-dimensional sensing structure of learning, we show that it is possible to train an agent to perform navigation-related tasks and obstacle avoidance without using complex sensing information. The proposed methodology was successfully used in three distinct simulated environments. Overall, it was shown that Double Deep structures further enhance the problem for the navigation of mobile robots when compared to the ones with simple Q structures.

Raul Steinmetz, Fabio Demo Rosa, Victor Augusto Kich et al.

Autonomous navigation of terrestrial robots using Reinforcement Learning (RL) from LIDAR observations remains challenging due to the high dimensionality of sensor data and the sample inefficiency of model-free approaches. Conventional policy networks struggle to process full-resolution LIDAR inputs, forcing prior works to rely on simplified observations that reduce spatial awareness and navigation robustness. This paper presents a novel model-based RL framework built on top of the DreamerV3 algorithm, integrating a Multi-Layer Perceptron Variational Autoencoder (MLP-VAE) within a world model to encode high-dimensional LIDAR readings into compact latent representations. These latent features, combined with a learned dynamics predictor, enable efficient imagination-based policy optimization. Experiments on simulated TurtleBot3 navigation tasks demonstrate that the proposed architecture achieves faster convergence and higher success rate compared to model-free baselines such as SAC, DDPG, and TD3. It is worth emphasizing that the DreamerV3-based agent attains a 100% success rate across all evaluated environments when using the full dataset of the Turtlebot3 LIDAR (360 readings), while model-free methods plateaued below 85%. These findings demonstrate that integrating predictive world models with learned latent representations enables more efficient and robust navigation from high-dimensional sensory data.

Victor Augusto Kich, Jair Augusto Bottega, Raul Steinmetz et al.

In this work, we present Curled-Dreamer, a novel reinforcement learning algorithm that integrates contrastive learning into the DreamerV3 framework to enhance performance in visual reinforcement learning tasks. By incorporating the contrastive loss from the CURL algorithm and a reconstruction loss from autoencoder, Curled-Dreamer achieves significant improvements in various DeepMind Control Suite tasks. Our extensive experiments demonstrate that Curled-Dreamer consistently outperforms state-of-the-art algorithms, achieving higher mean and median scores across a diverse set of tasks. The results indicate that the proposed approach not only accelerates learning but also enhances the robustness of the learned policies. This work highlights the potential of combining different learning paradigms to achieve superior performance in reinforcement learning applications.

Ricardo B. Grando, Raul Steinmetz, Victor A. Kich et al.

Deep Reinforcement Learning (DRL) has emerged as a promising approach to enhancing motion control and decision-making through a wide range of robotic applications. While prior research has demonstrated the efficacy of DRL algorithms in facilitating autonomous mapless navigation for aerial and terrestrial mobile robots, these methods often grapple with poor generalization when faced with unknown tasks and environments. This paper explores the impact of the Delayed Policy Updates (DPU) technique on fostering generalization to new situations, and bolstering the overall performance of agents. Our analysis of DPU in aerial and terrestrial mobile robots reveals that this technique significantly curtails the lack of generalization and accelerates the learning process for agents, enhancing their efficiency across diverse tasks and unknown scenarios.

Raul Steinmetz, Victor A. Kich, Henrique Krever et al.

Deep learning, particularly Convolutional Neural Networks (CNNs), has gained significant attention for its effectiveness in computer vision, especially in agricultural tasks. Recent advancements in instance segmentation have improved image classification accuracy. In this work, we introduce a comprehensive dataset for training neural networks to detect weeds and soy plants through instance segmentation. Our dataset covers various stages of soy growth, offering a chronological perspective on weed invasion's impact, with 1,000 meticulously annotated images. We also provide 6 state of the art models, trained in this dataset, that can understand and detect soy and weed in every stage of the plantation process. By using this dataset for weed and soy segmentation, we achieved a segmentation average precision of 79.1% and an average recall of 69.2% across all plant classes, with the YOLOv8X model. Moreover, the YOLOv8M model attained 78.7% mean average precision (mAp-50) in caruru weed segmentation, 69.7% in grassy weed segmentation, and 90.1% in soy plant segmentation.