Advancements in vision and depth sensing technologies have significantly enhanced perception systems in robotics and drone applications. This chapter explores novel approaches to depth perception, focusing on emerging sensor architectures and AI-driven methods. Event-based vision sensors offer ultra-low latency and high dynamic range, enabling real-time obstacle detection and high-speed manoeuvring in autonomous robots and drones. Innovations in LiDAR, including solid-state and frequency-modulated continuous wave (FMCW) systems, improve depth accuracy and velocity estimation for autonomous navigation. AI-powered depth estimation techniques, such as neural radiance fields (NeRFs) and self-supervised learning, allow robots and drones to infer depth from monocular images, reducing reliance on traditional depth sensors. Polarisation-based depth sensing enhances perception in challenging environments, such as reflective or transparent surfaces, improving robotic manipulation and aerial mapping. Multi-modal fusion strategies, integrating RGB-D cameras, LiDAR, and inertial measurement units (IMUs), enhance scene understanding for robust autonomous operations. Additionally, advancements in photonic imaging, meta surface optics, and time-of-flight (ToF) sensors contribute to high-resolution 3D reconstructions, further improving robotic vision and drone-based environmental monitoring. This chapter provides a comprehensive overview of these novel technologies, their applications, limitations, and future directions in robotic and drone perception systems.