In the field of agricultural robotics, robotic grippers play an indispensable role, directly influencing the rate of fruit damage and handling efficiency. Currently, traditional agricultural robotic grippers face challenges such as high damage rates and high requirements for position control. A robotic gripper for stable spherical fruit handling with high positional offset tolerance and a low fruit damage rate is proposed in this paper. It adopts a three-finger structure. A flexible active roller is configured at the end of each finger, allowing fruit translation with just a gentle touch. An integrated pressure sensor within the active roller further enhances the gripper’s compliance. To describe the effect of the gripper on the fruit, the interaction model was derived. Taking the tomato as a typical soft and fragile spherical fruit, three experiments were conducted to evaluate the performance of the proposed gripper. The experimental results demonstrated the handling capability of the gripper and the maximum graspable weight reached 2077 g. The average failure rate for the unilateral offset of 9 mm was only 1.33%, and for the bilateral offset of 6-6 mm was 4%, indicating the high positional offset tolerance performance and a low fruit damage rate of the gripper. The preliminary tomato-picking capability of the proposed gripper was also validated in a simplified laboratory scenario.

Traditional object detection methods for meat duck counting suffer from high manual costs, low image quality, and varying object sizes. To address these issues, this paper proposes FE-P Net, an image enhancement-based parallel density estimation network that integrates CNNs with Transformer models. FE-P Net employs a Laplacian pyramid to extract multi-scale features, effectively reducing the impact of low-resolution images on detection accuracy. Its parallel architecture combines convolutional operations with attention mechanisms, enabling the model to capture both global semantics and local details, thus enhancing its adaptability across diverse density scenarios. The Reconstructed Convolution Module is a crucial component that helps distinguish targets from backgrounds, significantly improving feature extraction accuracy. Validated on a meat duck counting dataset in breeding environments, FE-P Net achieved 96.46% accuracy in large-scale settings, demonstrating state-of-the-art performance. The model shows robustness across various densities, providing valuable insights for poultry counting methods in agricultural contexts.

Sport horse feeding robots face significant challenges in achieving precise navigation within complex stable environments. Uneven terrain and frequently moist ground often cause drive wheel slippage, resulting in path deviation and cumulative pose errors that compromise feeding accuracy and operational efficiency. To address this challenge, an enhanced Dynamic Window Approach (DWA) path planning framework, which integrates an automatic drift correction module based on an Inertial Measurement Unit (IMU) and a two-stage cascade proportional–integral–derivative (PID) controller, is proposed in this paper. This enhanced DWA enables precise yaw adjustment while preserving the native velocity sampling and trajectory evaluation framework of conventional DWA. Field validations were conducted through ten independent trials along a fixed 28 m feeding route in an actual sport horse feeding environment to quantitatively evaluate the robot’s path deviation and yaw angle stability. The results demonstrated that the enhanced algorithm reduced the standard deviation of path deviation from 0.161 m to 0.144 m (10.56% improvement) and decreased yaw angle standard deviation from 2.19° to 1.74° (20.55% reduction in angular oscillation). These improvements validated the effectiveness of the proposed algorithm in mitigating slippage-induced pose drift and significantly improving the locomotion capability of robots for sport horse feeding within stable environments.