Position-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learning

Martini, Mauro; Cerrato, Simone; Salvetti, Francesco; Angarano, Simone; Chiaberge, Marcello

doi:10.1109/case49997.2022.9926582

Cited by 30 publications

(7 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, their movement continues down the vineyard row [14]. Other work has been done with deep learning for navigation, where the robot learns to navigate to the end of a vineyard row, but it is also in continuous motion [15]. In the case where a robot would need to stop at specific locations to prune, the navigation of the robot had the locations inserted manually into its path [16].…”

Section: State Of the Artmentioning

confidence: 99%

Computer-Vision Based Real Time Waypoint Generation for Autonomous Vineyard Navigation with Quadruped Robots

Milburn¹,

Gamba

Fernandes

et al. 2023

2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

The VINUM project seeks to address the shortage of skilled labor in modern vineyards by introducing a cuttingedge mobile robotic solution. Leveraging the capabilities of the quadruped robot, HyQReal, this system, equipped with arm and vision sensors, offers autonomous navigation and winter pruning of grapevines reducing the need for human intervention. At the heart of this approach lies an architecture that empowers the robot to easily navigate vineyards, identify grapevines with unparalleled accuracy, and approach them for pruning with precision. A state machine drives the process, deftly switching between various stages to ensure seamless and efficient task completion. The system's performance was assessed through experimentation, focusing on waypoint precision and optimizing the robot's workspace for single-plant operations. Results indicate that the architecture is highly reliable, with a mean error of 21.5cm and a standard deviation of 17.6cm for HyQReal. However, improvements in grapevine detection accuracy are necessary for optimal performance. This work is based on a computer-vision-based navigation method for quadruped robots in vineyards, opening up new possibilities for selective task automation. The system's architecture works well in ideal weather conditions, generating and arriving at precise waypoints that maximize the attached robotic arm's workspace. This work is an extension of our short paper presented at the Italian Conference on Robotics and Intelligent Machines (I-RIM), 2022 [1].

show abstract

Section: State Of the Artmentioning

confidence: 99%

Computer-Vision Based Real Time Waypoint Generation for Autonomous Vineyard Navigation with Quadruped Robots

Milburn¹,

Gamba

Fernandes

et al. 2023

2023 IEEE International Conference on Autonomous Robot Systems and Competitions (ICARSC)

View full text Add to dashboard Cite

show abstract

“…Kyaw et al [18] employed DRL based on grid maps to solve the Traveling Salesman Problem (TSP), achieving path planning for robots in large, complex environments. Considering the capability of DRL to address optimization decision-making problems with less prior information, Martini et al [19] implemented position-agnostic autonomous navigation in vineyards using DRL, without the help of GPS and visual odometry technologies. Wang et al [13] developed a DRLbased movement planning method for kiwifruit-harvesting robots, converting traditional grid-based coverage path planning into a TSP problem focused on area traversal order.…”

Section: Introductionmentioning

confidence: 99%

Intermittent Stop-Move Motion Planning for Dual-Arm Tomato Harvesting Robot in Greenhouse Based on Deep Reinforcement Learning

Li,

Feng,

Zhang

et al. 2024

Biomimetics

View full text Add to dashboard Cite

Intermittent stop–move motion planning is essential for optimizing the efficiency of harvesting robots in greenhouse settings. Addressing issues like frequent stops, missed targets, and uneven task allocation, this study introduced a novel intermittent motion planning model using deep reinforcement learning for a dual-arm harvesting robot vehicle. Initially, the model gathered real-time coordinate data of target fruits on both sides of the robot, and projected these coordinates onto a two-dimensional map. Subsequently, the DDPG (Deep Deterministic Policy Gradient) algorithm was employed to generate parking node sequences for the robotic vehicle. A dynamic simulation environment, designed to mimic industrial greenhouse conditions, was developed to enhance the DDPG to generalize to real-world scenarios. Simulation results have indicated that the convergence performance of the DDPG model was improved by 19.82% and 33.66% compared to the SAC and TD3 models, respectively. In tomato greenhouse experiments, the model reduced vehicle parking frequency by 46.5% and 36.1% and decreased arm idleness by 42.9% and 33.9%, compared to grid-based and area division algorithms, without missing any targets. The average time required to generate planned paths was 6.9 ms. These findings demonstrate that the parking planning method proposed in this paper can effectively improve the overall harvesting efficiency and allocate tasks for a dual-arm harvesting robot in a more rational manner.

show abstract

“…DL has been used in many robotics applications where objects must be detected [ 2 ] or segmented [ 3 ] to address manipulation tasks, demonstrating competitive advantages compared to classic image processing algorithms in terms of accuracy and robustness. For instance, relevant works in the precision agriculture field have been proposed in recent years to support autonomous navigation [ 4 , 5 ], harvesting [ 6 ], and spraying [ 7 ]. Intelligent DL-based behaviors are also desired for visual-based robotic surgery to detect and segment instruments [ 8 , 9 ], and in many industrial robotic tasks [ 10 , 11 ].…”

Section: Introductionmentioning

confidence: 99%

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Marchionna

Pugliese

Martini

et al. 2023

Sensors

Self Cite

View full text Add to dashboard Cite

The game of Jenga is a benchmark used for developing innovative manipulation solutions for complex tasks. Indeed, it encourages the study of novel robotics methods to successfully extract blocks from a tower. A Jenga game involves many traits of complex industrial and surgical manipulation tasks, requiring a multi-step strategy, the combination of visual and tactile data, and the highly precise motion of a robotic arm to perform a single block extraction. In this work, we propose a novel, cost-effective architecture for playing Jenga with e.Do, a 6DOF anthropomorphic manipulator manufactured by Comau, a standard depth camera, and an inexpensive monodirectional force sensor. Our solution focuses on a visual-based control strategy to accurately align the end-effector with the desired block, enabling block extraction by pushing. To this aim, we trained an instance segmentation deep learning model on a synthetic custom dataset to segment each piece of the Jenga tower, allowing for visual tracking of the desired block’s pose during the motion of the manipulator. We integrated the visual-based strategy with a 1D force sensor to detect whether the block could be safely removed by identifying a force threshold value. Our experimentation shows that our low-cost solution allows e.DO to precisely reach removable blocks and perform up to 14 consecutive extractions in a row.

show abstract

Position-Agnostic Autonomous Navigation in Vineyards with Deep Reinforcement Learning

Cited by 30 publications

References 31 publications

Computer-Vision Based Real Time Waypoint Generation for Autonomous Vineyard Navigation with Quadruped Robots

Computer-Vision Based Real Time Waypoint Generation for Autonomous Vineyard Navigation with Quadruped Robots

Intermittent Stop-Move Motion Planning for Dual-Arm Tomato Harvesting Robot in Greenhouse Based on Deep Reinforcement Learning

Deep Instance Segmentation and Visual Servoing to Play Jenga with a Cost-Effective Robotic System

Contact Info

Product

Resources

About