ROKAE iNexus is an All-in-One open control system developed by ROKAE Robotics and unveiled at the company's 4th Global Partners Conference on 17 July 2026. iNexus is designed for wheeled dual-arm robots and embodied-intelligence applications.
It provides high-performance real-time motion control, an open interface architecture, and software ecosystem support. ROKAE positions iNexus as an embodied-intelligence "cerebellum" infrastructure and a ready-to-use, full-stack robotics development platform for embodied-intelligence developers and industry partners.
iNexus serves as the control layer for ROKAE's embodied-intelligence product line, which includes the AR Series force-controlled arms, the HSA Series integrated force-controlled joints, and the Helios wheeled dual-arm robot. It is a distinct product from the xCore control system used in ROKAE's industrial and collaborative robots.
A Control Stack is the set of software components responsible for control logic, motion planning, command execution, and coordination of a robot's actuators. It receives high-level goals or waypoints (from planning or AI layers) and translates them into low-level actuator commands, closed-loop feedback control, and safety checks. Common implementations include MoveIt (arm manipulation), Nav2 (mobile navigation), and custom whole-body control stacks for humanoids.
Physical AI platforms are software products that connect physical robots and industrial production processes with artificial intelligence models. Unlike a pure SDK or middleware, a Physical AI Platform ships as an end-to-end stack: perception, task planning, process parameter optimization, multi-robot coordination and operator UI. They target use cases such as surface treatment (grinding, painting, polishing), inspection, assembly and packing — where business value comes from combining hardware, AI and domain knowledge.
The real-time control role describes software responsible for closed control loops executed at a guaranteed, deterministic frequency — typically 1 to 10 kHz for current/torque loops in actuators. Unlike soft real-time, in a hard real-time regime missing a deadline is treated as a system error. Implemented on deterministic kernels (Linux PREEMPT_RT, QNX Neutrino RTOS) or dedicated microcontrollers. Critical for biped balance stability, force control, impedance control and functional safety.
Robot Control denotes the role of software responsible for motion control, command execution, coordination of actuating elements and the direct operational logic of the robot.
The Physical AI orchestration role describes software that ties perception, AI decisions and multi-robot control into a single production workflow. The orchestration layer assigns specific tasks to specific machines, monitors the real-time state of the process, tunes execution parameters (e.g. contact force, feed rate, motion trajectory) and reports production KPIs. It typically sits above the robot control layer and below ERP/MES.
