AI-Driven and Embodied Agricultural Robotics: From Intelligent Perception to Autonomous Field Operations

Dear Colleagues,

Artificial intelligence is reshaping agricultural robotics from automated machines into intelligent and embodied systems capable of perceiving, reasoning, planning, and acting in complex agricultural environments. Beyond conventional deep learning, recent advances in foundation models, vision–language models, embodied AI, robot learning, and autonomous decision-making are enabling agricultural robots to perform increasingly sophisticated tasks with greater autonomy and adaptability. These developments provide new opportunities to improve productivity, reduce labor dependency, and promote sustainable crop production across open fields, orchards, greenhouses, and other agricultural systems.

Despite this rapid progress, a significant gap remains between the development of AI algorithms and their effective implementation in complete agricultural robotic systems. Many studies demonstrate excellent performance in agricultural image classification, detection, or segmentation, yet these advances do not necessarily translate into improved robotic autonomy or operational performance. This Special Issue therefore focuses on AI technologies that directly enable robotic functions and autonomous operation, emphasizing the complete pipeline from intelligent perception and decision-making to planning, control, manipulation, and real-world deployment. We particularly encourage contributions that integrate AI methods into robotic systems and validate their effectiveness through robot-level experiments, closed-loop autonomous operation, or realistic field applications.

Topics of interest include, but are not limited to:

• Foundation models, multimodal AI, vision–language models, and embodied AI for agricultural robotics;
• Robot learning, autonomous decision-making, and intelligent task planning;
• Robot perception integrated with navigation, manipulation, harvesting, weeding, spraying, pruning, and crop management;
• Localization, mapping, SLAM, navigation, motion planning, and autonomous control;
• Agricultural manipulators, end-effectors, soft robotics, and robot mechanism design;
• Multi-robot systems, aerial–ground collaboration, cloud robotics, and digital twins;
• Integrated autonomous agricultural robotic systems and long-term field deployment;
• Benchmarking, evaluation, and real-world validation of agricultural robotic systems, including operational efficiency, reliability, robustness, and autonomy.

This Special Issue is intended for research that advances the autonomy, integration, and practical capability of agricultural robots. Contributions should preferably demonstrate robot-level validation and report performance indicators related to robotic operation, such as navigation accuracy, manipulation success rate, operational efficiency, reliability, robustness, or degree of autonomy. Stand-alone studies focusing solely on image classification, object detection, semantic or instance segmentation, or other AI model development, without direct integration into a robotic function or experimental relevance to robotic operation, are not within the primary focus of this Special Issue. Preference will be given to contributions demonstrating integrated robotic systems, hardware implementation, closed-loop autonomous operation, and comprehensive validation under realistic agricultural conditions.

Dr. Aichen Wang
Prof. Dr. Zhao Zhang
Prof. Dr. Jizhan Liu
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Agriculture is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

• agricultural robotics
• embodied AI
• robot perception
• autonomous navigation
• robotic manipulation
• intelligent control
• field robotics
• real-world deployment