Strategies to reduce slippage and disturbing wheel-terrain interactions are essential to improve navigation and motion control of field robots. Thus, this work proposes an integral control architecture based on a distributed tube-based nonlinear Model Predictive Control scheme to regulate tire dynamics and an adaptive model-based control scheme for trajectory tracking over deformable terrain. For the proposed control architecture, the overall system is decomposed into simpler subsystems to separately represent the four-tire driven motion dynamics (i.e., slip and sideslip) from that of the vehicle's pose and speeds. Since a vehicle and its tires have different dynamic response characteristics, cooperative agents of the distributed control strategy are able to exchange information between subsystems to attain evenly allocated drivetrain torques during slippery situations. The motion controller is made adaptive to terra-mechanical parameters with a Nonlinear Moving Horizon Estimation approach working under a parallel Real-Time Iteration scheme. Field experimentations in an industrial compact loader Cat ^° 262 C subject to off-road conditions demonstrated that the proposed approach was capable of reducing up to a minimum of 18.2% of tire slip and sidelip range of ±6.6 ^° when compared to its non-robust counterpart. Consequently, the proposed approach was also able to reduce lateral and longitudinal trajectory tracking errors by around 66.6% and 43.7%, respectively, which may have a direct impact on the resources of the machinery.

This article presents a combined route and path planning strategy to guide Skid–Steer Mobile Robots (SSMRs) in scheduled harvest tasks within expansive crop rows with complex terrain conditions. The proposed strategy integrates: (i) a global planning algorithm based on the Traveling Salesman Problem under the Capacitated Vehicle Routing approach and Optimization Routing (OR-tools from Google) to prioritize harvesting positions by minimum path length, unexplored harvest points, and vehicle payload capacity; and (ii) a local planning strategy using Informed Rapidly-exploring Random Tree (${\mathrm{IRRT}}^{*}$) to coordinate scheduled harvesting points while avoiding low-traction terrain obstacles. The global approach generates an ordered queue of harvesting locations, maximizing the crop yield in a workspace map. In the second stage, the ${\mathrm{IRRT}}^{*}$ planner avoids potential obstacles, including farm layout and slippery terrain. The path planning scheme incorporates a traversability model and a motion model of SSMRs to meet kinematic constraints. Experimental results in a generic fruit orchard demonstrate the effectiveness of the proposed strategy. In particular, the ${\mathrm{IRRT}}^{*}$ algorithm outperformed RRT and ${\mathrm{RRT}}^{*}$ with 96.1% and 97.6% smoother paths, respectively. The ${\mathrm{IRRT}}^{*}$ also showed improved navigation efficiency, avoiding obstacles and slippage zones, making it suitable for precision agriculture.

Autonomous navigation in mining environments is challenged by complex wheel–terrain interaction, traction losses caused by slip dynamics, and sensor limitations. This paper investigates the effectiveness of Deep Reinforcement Learning (DRL) techniques for the trajectory tracking control of skid-steer mobile robots operating under terra-mechanical constraints. Four state-of-the-art DRL algorithms, i.e., Proximal Policy Optimization (PPO), Deep Deterministic Policy Gradient (DDPG), Twin Delayed DDPG (TD3), and Soft Actor–Critic (SAC), are selected to evaluate their ability to generate stable and adaptive control policies under varying environmental conditions. To address the inherent partial observability in real-world navigation, this study presents an original approach that integrates Long Short-Term Memory (LSTM) networks into DRL-based controllers. This allows control agents to retain and leverage temporal dependencies to infer unobservable system states. The developed agents were trained and tested in simulations and then assessed in field experiments under uneven terrain and dynamic model parameter changes that lead to traction losses in mining environments, targeting various trajectory tracking tasks, including lemniscate and squared-type reference trajectories. This contribution strengthens the robustness and adaptability of DRL agents by enabling better generalization of learned policies compared with their baseline counterparts, while also significantly improving trajectory tracking performance. In particular, LSTM-based controllers achieved reductions in tracking errors of 10%, 74%, 21%, and 37% for DDPG-LSTM, PPO-LSTM, TD3-LSTM, and SAC-LSTM, respectively, compared with their non-recurrent counterparts. Furthermore, DDPG-LSTM and TD3-LSTM reduced their control effort through the total variation in control input by 15% and 20% compared with their respective baseline controllers, respectively. Findings from this work provide valuable insights into the role of memory-augmented reinforcement learning for robust motion control in unstructured and high-uncertainty environments.