Advancements in Robotic Agriculture and Tactile Sensing

The field of robotic agriculture and tactile sensing is witnessing significant advancements, driven by the need for efficient, sustainable, and precise practices. Researchers are exploring innovative methods for automated fruit handling, including quantitative hardness assessment and adaptive manipulation. Vision-based tactile sensing is emerging as a promising approach for rapid, non-destructive evaluation of fruit properties. Furthermore, the development of adaptive wiping methods and autonomous robotic pruning systems is addressing critical challenges in precision agriculture. Noteworthy papers in this area include the proposal of a novel framework for quantitative hardness assessment utilizing vision-based tactile sensing, which has demonstrated efficacy and robustness in extensive experimental validation. Another notable work is the introduction of an adaptive wiping method that integrates real-time force-torque feedback with pre-trained object representations, achieving 96% accuracy in applying reference forces.

Sources

Quantitative Hardness Assessment with Vision-based Tactile Sensing for Fruit Classification and Grasping

Adaptive Wiping: Adaptive contact-rich manipulation through few-shot imitation learning with Force-Torque feedback and pre-trained object representations

Autonomous Robotic Pruning in Orchards and Vineyards: a Review

The RaspGrade Dataset: Towards Automatic Raspberry Ripeness Grading with Deep Learning

Utilization of Skin Color Change for Image-based Tactile Sensing

Built with on top of