Search for: All records

Mobile robot navigation is a critical aspect of robotics, with applications spanning from service robots to industrial automation. However, navigating in complex and dynamic environments poses many challenges, such as avoiding obstacles, making decisions in real-time, and adapting to new situations. Reinforcement Learning (RL) has emerged as a promising approach to enable robots to learn navigation policies from their interactions with the environment. However, application of RL methods to real-world tasks such as mobile robot navigation, and evaluating their performance under various training–testing settings has not been sufficiently researched. In this paper, we have designed an evaluation framework that investigates the RL algorithm’s generalization capability in regard to unseen scenarios in terms of learning convergence and success rates by transferring learned policies in simulation to physical environments. To achieve this, we designed a simulated environment in Gazebo for training the robot over a high number of episodes. The training environment closely mimics the typical indoor scenarios that a mobile robot can encounter, replicating real-world challenges. For evaluation, we designed physical environments with and without unforeseen indoor scenarios. This evaluation framework outputs statistical metrics, which we then use to conduct an extensive study on a deep RL method, namely the proximal policy optimization (PPO). The results provide valuable insights into the strengths and limitations of the method for mobile robot navigation. Our experiments demonstrate that the trained model from simulations can be deployed to the previously unseen physical world with a success rate of over 88%. The insights gained from our study can assist practitioners and researchers in selecting suitable RL approaches and training–testing settings for their specific robotic navigation tasks. 

Abstract Submarine groundwater discharge (SGD), comprising both nearshore and offshore components, plays a vital role in water cycling and solute transport in coastal areas, and affects coastal marine ecosystems. Previous estimations of SGD based on seepage meters, geochemical tracers, water balances, analytical, and numerical approaches frequently overlooked offshore contributions driven by oceanic currents, waves, and tides, resulting in an incomplete understanding of SGD dynamics and its ecological consequences. Therefore, this study quantified the total SGD by integrating offshore (current‐, wave‐, and tide‐driven SGD) and nearshore (fresh SGD and tide‐driven SGD) components in Florida coasts. The calculated total SGD was approximately 15.08% of annual precipitation volume in Florida, with 14.09% offshore SGD (0.7%, 8.2%, and 5.2% from currents, waves, and tides, respectively) and ∼0.986% nearshore SGD (0.44% and 0.55% from fresh and recirculated SGD), underscoring offshore SGD as a major driver of groundwater discharge extending across the continental shelf. Moreover, nearshore SGD‐derived dissolved inorganic nutrient fluxes were estimated as kg/yr for nitrogen and kg/yr for phosphorus, whereas offshore SGD‐derived nutrients were kg/yr for nitrogen and kg/yr for phosphorus. On average, these nutrient inputs were approximately 6 and 4 times greater than those from surface water nutrient fluxes from coastal river discharge for dissolved inorganic nitrogen and dissolved inorganic phosphorus, respectively, highlighting the significant role of SGD in nutrient cycling in Florida. Additionally, we identified 54 SGD hotspots, which are generally aligned spatially with the distribution of coastal springs. Therefore, future research should evaluate the impact on nutrient loads to enhance coastal water management and sustainability.