The great success of the Sojourner rover in the Mars Pathfinder mission set off a global upsurge of planetary exploration with autonomous wheeled mobile robots(WMRs),or rovers.Planetary WMRs are among the most intelligent space systems that combine robotic intelligence(robint),virtual intelligence(virtint),and human intelligence(humint) synergetically.This article extends the architecture of the three-layer intelligence stemming from successful Mars rovers and related technologies in order to support the R&D of future tele-operated robotic systems.Double-layer human-machine interfaces are suggested to support the integration of humint from scientists and engineers through supervisory(Mars rovers) or three-dimensional(3D) predictive direct tele-operation(lunar rovers).The concept of multilevel autonomy to realize robint,in particular,the Coupled-Layer Architecture for Robotic Autonomy developed for Mars rovers,is introduced.The challenging issues of intelligent perception(proprioception and exteroception),navigation,and motion control of rovers are discussed,where the terrains’ mechanical properties and wheel-terrain interaction mechanics are considered to be key.Double-level virtual simulation architecture to realize virtint is proposed.Key technologies of virtint are summarized:virtual planetary terrain modeling,virtual intelligent rover,and wheel-terrain interaction mechanics.This generalized three-layer intelligence framework is also applicable to other systems that require human intervention,such as space robotic arms,robonauts,unmanned deep-sea vehicles,and rescue robots,particularly when there is considerable time delay. The great success of the Sojourner rover in the Mars Pathfinder mission set off global upsurge of planetary exploration with autonomous wheeled mobile robots (WMRs), or rovers. Palanetary WMRs are among the most intelligent space systems that combines robotic intelligence (robint), virtual intelligence (virtint), and human intelligence (humint) synergetically.This article extends the architecture of the three-layer intelligence stemming from successful Mars rovers and related technologies in order to support the R & D of future tele-operated robotic systems. Double-layer human -machine interfaces are suggested to support the integration of humint from scientists and engineers through supervisory (Mars rovers) or three-dimensional (3D) predictive direct tele-operation (lunar rovers). The concept of multilevel autonomy to realize robint, in particular, the Coupled-Layer Architecture for Robotic Autonomy developed for Mars rovers, is introduced. The challenging issues of intelligent perception (proprioception and exteroception), navigation, and motion control of rovers are discussed, where the terrains’ mechanical properties and wheel-terrain interaction mechanics are considered to be key. Double-level virtual simulation architecture to realize virtint is proposed. Key technologies of virtint. : virtual planetary terrain modeling, virtual intelligent rover, and wheel-terrain interaction mechanics. This generalized three-layer intelligence framework is also applicable to other systems that require human intervention, such as space robotic arms, robonauts, unmanned deep-sea vehicles, and rescue robots, particularly when there is considerable time delay