Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows

Aghi, Diego; Cerrato, Simone; Mazzia, Vittorio; Chiaberge, Marcello

doi:10.1109/iros51168.2021.9635969

Cited by 19 publications

(12 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Their optimized model (RTSD-Net) with TensorRT achieved about 25.20 fps and performed 15% faster than the original YOLOv4-tiny model on Jetson Nano without significant loss of accuracy. Other promising applications of Edge-AI are air temperature forecasting [ 109 ], environment monitoring [ 110 ], autonomous navigation systems [ 111 ] and so on.…”

Section: Future Prospects/directionsmentioning

confidence: 99%

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

Mahmud

Zahid

Das

2023

Sensors

View full text Add to dashboard Cite

The ornamental crop industry is an important contributor to the economy in the United States. The industry has been facing challenges due to continuously increasing labor and agricultural input costs. Sensing and automation technologies have been introduced to reduce labor requirements and to ensure efficient management operations. This article reviews current sensing and automation technologies used for ornamental nursery crop production and highlights prospective technologies that can be applied for future applications. Applications of sensors, computer vision, artificial intelligence (AI), machine learning (ML), Internet-of-Things (IoT), and robotic technologies are reviewed. Some advanced technologies, including 3D cameras, enhanced deep learning models, edge computing, radio-frequency identification (RFID), and integrated robotics used for other cropping systems, are also discussed as potential prospects. This review concludes that advanced sensing, AI and robotic technologies are critically needed for the nursery crop industry. Adapting these current and future innovative technologies will benefit growers working towards sustainable ornamental nursery crop production.

show abstract

Section: Future Prospects/directionsmentioning

confidence: 99%

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

Mahmud

Zahid

Das

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…Unlike the previous method, the authors of [ 41 ] exploited a custom-trained segmentation network and a low-RGB camera to produce smooth trajectories and stable control in different vineyard scenarios. Although the method showed outstanding results, this framework cannot be directly translated into an unstructured, dynamic environment, such as a sidewalk.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning-Based NMPC for Local Motion Planning of Last-Mile Delivery Robot

Imad

Doukhi²,

Lee³

et al. 2022

Sensors

View full text Add to dashboard Cite

Feasible local motion planning for autonomous mobile robots in dynamic environments requires predicting how the scene evolves. Conventional navigation stakes rely on a local map to represent how a dynamic scene changes over time. However, these navigation stakes depend highly on the accuracy of the environmental map and the number of obstacles. This study uses semantic segmentation-based drivable area estimation as an alternative representation to assist with local motion planning. Notably, a realistic 3D simulator based on an Unreal Engine was created to generate a synthetic dataset under different weather conditions. A transfer learning technique was used to train the encoder-decoder model to segment free space from the occupied sidewalk environment. The local planner uses a nonlinear model predictive control (NMPC) scheme that inputs the estimated drivable space, the state of the robot, and a global plan to produce safe velocity commands that minimize the tracking cost and actuator effort while avoiding collisions with dynamic and static obstacles. The proposed approach achieves zero-shot transfer from a simulation to real-world environments that have never been experienced during training. Several intensive experiments were conducted and compared with the dynamic window approach (DWA) to demonstrate the effectiveness of our system in dynamic sidewalk environments.

show abstract

“…The segmentation masks Xseg ∈ R h×w provided by the deep neural network are post-processed and fed into a custom control algorithm in order to generate consistent velocity commands to drive the UGV inside the inter-row space and maintain as much as possible the inter-row centrality. As in [47], we compute a sum of S segmentation maps along with an intersection with depth information provided by an RGB-D camera in order to obtain a more stable control. First, we pick S consecutive segmentation maps at times {t − S, ..., t} and we fuse them…”

Section: Segmentation-based Controlmentioning

confidence: 99%

“…In the X t ctrl binary map 1 stands for obstacles and 0 freespace. The segmentation-based control algorithm is developed building over the SPC algorithm presdented in [47]. Indeed, we propose a simplified version of that control function to avoid useless conditional blocks and obtain a more real-time control algorithm.…”

Section: Segmentation-based Controlmentioning

confidence: 99%

“…with x c center coordinate of the selected cluster. Equation ( 9) represents the angular velocity control function, while equation (10) has been used to compute the linear velocity, as in [48] and [47]. Eventually, the control velocity commands sent to the actuators are smoothed using the Exponential Moving Average (EMA), formalized in equation ( 12), in order to prevent the mobile platform from sharp motion.…”

Section: Segmentation-based Controlmentioning

confidence: 99%

See 1 more Smart Citation

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Cerrato¹,

Mazzia²,

Salvetti³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

Expensive sensors and inefficient algorithmic pipelines significantly affect the overall cost of autonomous machines. However, affordable robotic solutions are essential to practical usage, and their financial impact constitutes a fundamental requirement to employ service robotics in most fields of application. Among all, researchers in the precision agriculture domain strive to devise robust and cost-effective autonomous platforms in order to provide genuinely large-scale competitive solutions. In this article, we present a complete algorithmic pipeline for row-based crops autonomous navigation, specifically designed to cope with low-range sensors and seasonal variations. Firstly, we build on a robust data-driven methodology to generate a viable path for the autonomous machine, covering the full extension of the crop with only the occupancy grid map information of the field. Moreover, our solution leverages on latest advancement of deep learning optimization techniques and synthetic generation of data to provide an affordable solution that efficiently tackles the well-known Global Navigation Satellite System unreliability and degradation due to vegetation growing inside rows. Extensive experimentation and simulations against computer-generated environments and real-world crops demonstrated the robustness and intrinsic generalizability of our methodology that opens the possibility of highly affordable and fully autonomous machines.

show abstract

Deep Semantic Segmentation at the Edge for Autonomous Navigation in Vineyard Rows

Cited by 19 publications

References 34 publications

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

Sensing and Automation Technologies for Ornamental Nursery Crop Production: Current Status and Future Prospects

Deep Learning-Based NMPC for Local Motion Planning of Last-Mile Delivery Robot

A Deep Learning Driven Algorithmic Pipeline for Autonomous Navigation in Row-Based Crops

Contact Info

Product

Resources

About