Successor is a software platform developed by Kawasaki Robotics aimed at "transferring expert knowledge to robots" — in practice, remote control and Learning from Demonstration (LfD). An expert operator works from a remote console with haptics, controlling a Kawasaki robot (e.g. Duaro, BX) in teleoperation mode while the system records trajectories, forces, and grip parameters. ML models trained on the collected recordings then perform tasks autonomously and, when in doubt, ask the operator for help.
The Successor architecture has three layers: (1) Operator Console — a station with VR/haptics, (2) Cloud Knowledge Base — storage for recordings and trained policies, (3) Robot Runtime — a module running on Kawasaki E/F/R-series controllers that executes policies autonomously. The system also supports shared-autonomy mode, where one operator supervises several robots at once.
Successor is a commercial Kawasaki product available only to industrial customers under support contracts. There is no public SDK. Deployments cover automotive, electronics, and logistics industries in Japan, Korea, and the US. The platform has been actively developed since 2017 and showcased at iREX and CES trade shows.
A Runtime is the environment or execution layer used to run code, load libraries, manage dependencies, and operate applications or services — either in real time or during normal system operation. In robotics this includes real-time operating system (RTOS) runtimes, ROS 2 executor runtimes, containerised execution environments (Docker, podman), and embedded C++ runtimes on microcontrollers.
Teleoperation encompasses systems and tools that enable a human operator to remotely control a robot — its manipulators, locomotion, cameras, grippers, or task execution — typically over a network connection. It ranges from low-latency direct joint-space control to higher-level task-space teleoperation with haptic feedback, and is widely used in inspection, surgery, hazardous environment work, and data collection for imitation learning.
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.
Fleet Management software encompasses tools designed for managing a fleet of robots: task allocation and scheduling, status monitoring, over-the-air (OTA) firmware and software updates, error handling, and multi-unit coordination. It provides a centralised operations layer above individual robot controllers and is critical in warehouse automation, last-mile delivery, and industrial inspection deployments.
Automotive production lines in Japan (Toyota, Mazda, Subaru), electronics factories in Korea, logistics warehouses in the US. Number of installed robots >1000 (2025).
No open-source community. Support via Kawasaki Robotics regional offices and integrator partners. Showcased at iREX, CES, and automatica.
Requires a Kawasaki service contract and specialized haptics (3D Systems Touch X or Force Dimension Sigma 7).
License family: Proprietary – Commercial
LfD support with foundation models (vision-language tasks).
Integration with Kawasaki BX-series, VR teleoperation.
Cloud Knowledge Base, shared autonomy mode.
First Successor showcase at iREX 2017.
