This article presents a novel path planning approach for robotic manipulators operating in complex factory farming environments, where traditional methods struggle with strict obstacle avoidance constraints. The proposed method strikes a balance between minor permissible collisions and efficient obstacle avoidance. First, scene point clouds are downsampled using voxelization to generate a cost map. A greedy search is then employed to determine an initial obstacle-aware Cartesian path from this map. After postprocessing, the Cartesian path is converted into joint configuration trajectories using Ranged-IK, ensuring smooth, singularity-free transitions with controlled flexibility. The resulting validated trajectories are executed by the manipulator. Experiments were conducted on two robotic manipulators for pollination and harvesting tasks. The results indicate that the proposed method outperforms common alternatives, achieving higher operational efficiency, success rates, and adaptability, while permitting minor collisions.
This paper presents a novel approach to developing control strategies for mobile robots, specifically the Pegasus, a bionic wheel-legged quadruped robot with unique chassis mechanics that enable four-wheel independent steering and diverse gaits. A multi-agent (MA) reinforcement learning (RL) controller is proposed, treating each leg as an independent agent with the goal of autonomous learning. The framework involves a multi-agent setup to model torso and leg dynamics, incorporating motion guidance optimization signal in the policy training and reward function. By doing so, we address leg schedule patterns for the complex configuration of the Pegasus, the requirement for various gaits, and the design of reward functions for MA-RL agents. Agents were trained using two variations of policy networks based on the framework, and real-world tests show promising results with easy policy transfer from simulation to the actual hardware. The proposed framework models acquired higher rewards and converged faster in training than other variants. Various experiments on the robot deployed framework showed fast response (0.8 s) under disturbance and low linear, angular velocity, and heading error, which was 2.5 cm/s, 0.06 rad/s, and 4°, respectively. Overall, the study demonstrates the feasibility of the proposed MA-RL control framework.
16 February 2026 in IEEE Transactions on Automation Science and Engineering
Autonomous weeding robots offer significant potential for reducing labor and environmental costs in precision agriculture. However, most systems decouple chassis locomotion from manipulator control, limiting efficiency in unstructured environments. We present LSTM-PPO-Weeding, an end-to-end framework unifying mobility and manipulation via memory-augmented reinforcement learning (RL). A high-speed region of interest (ROI) filter abstracts camera input into three-dimensional weed/crop poses, enabling the system to focus solely on task-relevant features. To mitigate challenges arising from occlusion and partial observability, we integrate long short-term memory (LSTM) into the proximal policy optimization (PPO) algorithm, establishing the proposed LSTM-PPO framework. The agent learns coordinated actions through a custom reward function balancing speed and precision. Experiments in simulation and real-world greenhouse settings show that LSTM-PPO-Weeding improves throughput while maintaining high accuracy. Compared to baseline methods, our approach reduces average weeding time by up to 74% with minimal loss in success rate, demonstrating its robustness for agricultural mobile manipulation.
1 January 2026 in IEEE Transactions on Industrial Electronics