Advances in Development and Application of Perception Sensors

Dear Colleagues,

Perception sensors are devices designed to emulate human senses, acting as the eyes, ears, and sense of touch for a machine. This enables them to effectively understand and interpret their physical environment. These sensors collect raw data from various physical magnitudes—such as distance, light intensity, sound, or temperature—converting them into corresponding electrical signals. These electrical signals are then digitized, allowing a computer to process the information. This allows machines to make decisions and perform tasks like detecting obstacles, recognizing objects, navigating spaces autonomously, performing actuation, and interacting with the real environmental elements. While perception sensors have advanced dramatically, they are far from being completely solved and integrated, and numerous open research challenges push the boundaries of robotics, AI, and material science. The core issue is bridging the robustness gap between machine perception and human perception. Machines can excel in specific, structured tasks but often fail in the unpredictable, messy real world.

This Special Issue aims to study, but is not limited to, the following topics:

• Deep Sensor Fusion Architectures.
• Cross-modal Self-Supervised Learning for fusion.
• Dynamic Sensor Fusion.
• Uncertainty Quantification for multi-sensor systems.
• Lifelong Learning and Online Adaptation of fusion models.
• Handling contradictory information from different sensors.
• Perception in Adverse Weather.
• Robustness to sensor degradation.
• Domain adaptation and generalization with limited target data.
• Zero-shot or few-shot learning for novel objects and environments.
• Addressing "long-tail" problems and edge cases.
• Deblurring and correcting for motion artifacts.
• Algorithm development for Event-Based Cameras.
• Neuromorphic sensor-processor co-design.
• Solid-State LiDAR (optical phased arrays, MEMS).
• High-resolution, low-cost radar imaging.
• Advanced Tactile Sensing (e-skin, flexible sensors).
• Sensor fusion with thermal/IR cameras.
• Low-light and ultra-high dynamic range (HDR) sensing.
• Real-time perception algorithms for embedded systems.
• Model compression and quantization for sensor data networks.
• Hardware acceleration (ASIC/FPGA) for specific sensor modalities.
• Power-efficient sensing and processing.
• Edge computing vs. cloud offloading strategies for perception.
• Physical Adversarial Attacks on perception systems (e.g., object spoofing).
• Defense and robust training against sensor spoofing.
• Formal Verification of perception models for safety-critical applications.
• Anomaly detection and fault diagnosis in sensor systems.
• Secure and trustworthy sensor data communication.
• 4D Perception (3D + time for dynamic scene forecasting).
• Intent and trajectory prediction of other agents.
• Context-aware perception (using scene context to improve detection).
• Vision–Language Models for sensor data interpretation.
• Egocentric perception for human–robot interaction.
• Learning the physics of the scene from sensor data.
• Standardized benchmarking and datasets for multi-sensor perception.
• Calibration and self-calibration of multi-sensor systems.
• Simulation-to-Reality (Sim2Real) transfer for sensor data.
• Cooperative Perception (V2X—Vehicle-to-Everything).
• Sustainable and eco-friendly sensor manufacturing and disposal.
• Ethical considerations and privacy in pervasive sensing.
• Perception Sensors for Autonomous Navigation Vehicles.
• Sonar sensors for underwater vehicles.

Prof. Dr. Fabian N. Murrieta-Rico
Dr. Wendy Flores-Fuentes
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. Applied Sciences 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 2400 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.

• perception sensors
• sensor fusion
• multi-sensor system
• sensor data communication