AI for Sensor-Based Robotic Object Perception

Dear Colleagues,

This Special Issue (SI) aims to present scholarly papers addressing efficient robotic object perception problems from the perspective of AI for sensor-based perception, which leverages artificial intelligence techniques to enable robots to interpret and understand their surroundings through diverse sensors, mimicking how humans integrate multi-sensory inputs to navigate and interact with the world. This approach is critical for robotic systems, as it allows them to perceive objects, environments, and tasks dynamically, adapting to new scenarios with the intelligence to process, learn from, and act on sensor data. A key question arises: “how can AI empower sensor-based perception to enhance robotic capabilities?” To explore this, we invite scientists, researchers, robotic specialists, and academics to share their insights into advancing AI techniques that elevate sensor-driven perception. What role does AI play in fusing data from visual, auditory, tactile, or LiDAR sensors for more robust perception? How can AI models be optimized to handle noisy, incomplete, or real-time sensor inputs? Can AI enable robots to learn from sensor data incrementally, improving their perception over time—similarly to how humans refine their understanding through experience? 

Overall, this Special Issue focuses on AI-driven solutions for sensor-based robotic perception tasks, such as object classification, object detection, semantic segmentation, robot navigation, SLAM, and many others. The topics of interest include (but are not limited to) the following areas:

• AI models for multi-sensor data fusion (e.g., vision, audio, touch, and LiDAR);
• Deep learning architectures optimized for real-time sensor processing;
• Few-/zero-shot learning for sensor-based perception;
• Embodied AI for sensor-driven robotic interaction;
• Federated learning for collaborative sensor data analysis;
• Meta-learning to enable rapid adaptation to new sensor inputs;
• Self-supervised learning from unlabeled sensor data;
• Domain adaptation for robust perception across varying sensor conditions;
• Semi-supervised and unsupervised learning for sensor data interpretation;
• Lifelong/continual learning to refine sensor-based perception over time.

Dr. Gan Sun
Dr. Zhenyu Lu
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 100 words) can be sent to the Editorial Office for announcement on this website.

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-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors 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.