Powered by a new Gen 5 SoC, the D585 Pro delivers 2x better depth quality and 2.5x better close-range performance, while new Perception Studio software brings advanced AI and perception capabilities to the broader RealSense ecosystem
CHICAGO — June 18, 2026 — At Automate 2026, RealSense is unveiling the RealSense™ D585 Pro, a new AI-native depth camera that combines advanced depth sensing, edge AI acceleration and a software-defined platform designed to improve over time through SDK-delivered capabilities.
Powered by a proprietary Gen 5 system-on-chip (SoC), the D585 Pro delivers over 2x better depth quality than the previous generation of RealSense cameras and 2.5x better close-range performance than competing solutions, enabling more precise navigation, manipulation, inspection and human-robot interaction. With on-device AI processing, the camera delivers full depth and image processing pipeline, reducing reliance on host computing resources while opening the door to a new generation of intelligent robotic applications.
The D585 Pro camera is being demonstrated live at Automate, Booth 12036, at McCormick Place in Chicago. Designed for humanoid robots, autonomous mobile robots (AMRs), collaborative arms, industrial robotics and inspection systems, the D585 combines a sub-15cm minimum range at full resolution, a 120×100° field of view (FOV) at 60 FPS, IP65 protection as standard and an AI inference engine that runs directly on the camera at the edge.
The camera is currently being evaluated by multiple global developers of humanoid robots, AMRs and robotic arms as they seek to simplify perception stacks, reduce system complexity and deploy AI-powered vision closer to the edge.
“The D585 Pro is not just an update to what came before; it’s the actualization of the Visual Cortex of Physical AI™,” said Nadav Orbach, RealSense CEO. “For the first time, developers can deploy a single depth camera that operates from under 15 centimeters to more than 10 meters, indoors or outdoors, while gaining new capabilities over time through software updates rather than hardware replacement. The early response from leading robotics companies has reinforced our belief that the industry is ready for a new generation of perception platforms that combine depth sensing, AI and software-defined capabilities in a single device.”
Built on a New Gen 5 Architecture
The D585 Pro introduces a new hardware architecture built around a custom Gen 5 SoC featuring a depth engine, image signal processor (ISP), digital signal processor (DSP), dedicated AI accelerators, and a quad-core ARM processor, combined with dual IR projectors and high-resolution sensors. The result is a new benchmark in performance across every dimension that matters for robotics and industrial automation.
Key specifications at launch:
- 120×100° FOV, optimized for Visual SLAM, navigation and whole-scene awareness.
- Dual RGB, delivers depth and imaging for VLAs and world models, and enables a path from tele-operation to fully autonomous robots
- 2x better depth quality, across the entire FOV, with finer detail visibility, 2x noise reduction and dramatically reduced temporal flicker.
- Sub-15cm minimum range at full resolution, 2.5x better than the nearest competitor, it enables close-range applications, including cobot arm inspection, bin picking and shelf scanning that traditional depth cameras cannot support.
- 60 FPS at 1280×960, double the frame rate of 30 FPS class competitors, sustaining full-resolution capture on fast-moving robots and high-speed conveyors.
- 10m+ operating range at optimal accuracy, covering the full navigation envelope for AMR fleets in warehouse and factory environments.
- IP65 as standard, on every unit, with no premium SKU required.
- GMSL2 + USB-C connectivity, with hardware sync support for GPU and x86 deployments.
- Built-in IR filters, for reliable operation in bright outdoor sunlight and low-light indoor environments.
AI-Native and Software-Defined
The D585 Pro ships with on-camera enhanced depth processing and person detection in beta at launch, running entirely on the Gen 5 SoC without requiring host compute. Planned SDK releases will add capabilities, including Visual-Inertial Odometry (VIO), occupancy grid generation, auto-calibration, face detection, to existing D585 hardware via software update after general availability. This approach enables customers to deploy hardware once while continuously expanding functionality over the life of the system.
Optional Depth Compression is available. Depth Compression is RealSense’s on-camera active noise reduction that condenses a 2×2-pixel block into a single-precision depth datapoint, reducing depth-stream bandwidth by 75% with no loss of detail or accuracy. For bandwidth-constrained deployments and continuous high-frame-rate streaming, Depth Compression removes a critical infrastructure bottleneck without sacrificing depth quality.
Also available at launch, Dual RGB enables simultaneous 30 FPS RGB and 30 FPS depth streams at up to 1280×960, merged on camera with no host CPU overhead. The feature is designed for humanoid robots, inspection pipelines, digital twins and workflows that require synchronized color and depth data.
RealSense Introduces Perception Studio Beta Program
Alongside the D585 Pro, RealSense today announced RealSense Perception Studio, a new beta program for advanced capabilities within the RealSense 2.0 SDK. Available this month as downloadable binaries for registered developers, Perception Studio provides early access to new perception technologies across the RealSense ecosystem.
Initial beta features include:
- Close-range depth performance, extending depth sensing to under 3cm on the D401 and D405, and under 15cm across the D400-series family.
- Person Detection, enabling enhanced safety and human-awareness applications.
- Visual-Inertial Odometry (VIO) with cuSLAM, executed on an NVIDIA host and optimized for RealSense RGB and depth streams.
Ready for Business
The D585 Pro’s combination of close-range precision, long-range coverage, high frame rate and indoor/outdoor performance makes it the first single-camera platform capable of spanning the full robotics and industrial vision stack. Built-in IR filters deliver consistent depth performance in both bright outdoor sunlight and low-light indoor environments, with no configuration changes or auxiliary hardware. Dual active projectors provide immunity to harsh ambient lighting and repetitive patterns that defeat passive stereo systems, making the D585 Pro viable in conditions where competing cameras fail.
Primary use cases include:
- Humanoid Robots: Dual RGB for simultaneous RGB and depth awareness for manipulation, navigation, teleoperation and human interaction, as well as VLA training and world models.
- AMR Navigation: Autonomous mobile robots requiring obstacle avoidance, localization, mapping and corridor-scale navigation.
- Cobot Arm Inspection: Collaborative robots performing inspection, tolerance verification and defect detection during motion.
- Assembly Line and Conveyor Scanning: Industrial automation systems supporting assembly verification, conveyor scanning and high-speed quality-control workflows.
Availability
The RealSense D585 Pro is expected to begin shipping in Q1 2027. For additional information, technical specifications and developer resources, visit RealSenseai.com.
For live demonstrations at Automate 2026, visit RealSense at Booth 12036.
About RealSense
RealSense™ delivers the Visual Cortex of Physical AI™ through industry-leading depth cameras and vision technology used in autonomous mobile and humanoid robots, access control, industrial automation, healthcare and more. With a mission to deliver world-class perception systems for Physical AI and safely integrate robotics and AI into everyday life, RealSense provides intelligent, secure and reliable vision systems that help machines navigate and interact with the human world. The company is headquartered in Cupertino, California, with operations worldwide.