Robot control switches smartly between human and autonomous guidance
TEAR: Task-Evidence Authority Routing for Robotic Manipulation
Robotics
Summary
Robots that work in changing conditions need to decide when to listen to humans and when to act on their own. The authors present TEAR, a system that helps robots choose whether a human or autonomous controller should be in charge at any moment. TEAR looks at network quality and how well the robot’s autonomous actions fit the task to make smart decisions about control. This approach lets robots succeed almost as well as full human control but with much less human intervention.
What this means in practice
- •For field robotics operators: Manage robot control to balance human teleoperation and autonomy in environments with unstable networks.
- •For industrial automation engineers: Improve robotic manipulators by intelligently switching control sources to handle ambiguous or unexpected tasks.
Authors
Shicheng Zhang, Hui Liu, Haoliang Li
Abstract
Reliable robotic manipulation in field-deployed settings requires more than executing a capable controller. As the execution conditions change, the system must decide, online and on the robot side, which control source should hold authority. Human teleoperation adapts readily to contact-rich and semantically ambiguous situations but depends on a stable communication link. Local autonomy is executed without continuous human intervention, but may fail under semantic ambiguity, long-horizon drift, and unforeseen contingencies. These two control sources exhibit complementary reliability profiles. We formulate this complementarity as a control authority routing problem and present Task-Evidence Authority Routing for Robotic Manipulation (TEAR), an edge-deployable framework that allocates authority between human teleoperation and local autonomy. TEAR arbitrates on the robot side using network-state evidence, which governs the usability of teleoperation, and task-semantic evidence, which reflects whether autonomous execution remains consistent with the current task. A lightweight temporal arbitrator observes both forms of evidence together with robot state and current authority to time authority transfers. Across simulated and real-world trials under dynamic network conditions, TEAR achieves task success rates close to pure teleoperation while limiting teleoperation to 19.8-27.4% of control steps and improves success by 30-40% over autonomy-only execution in our settings. These results demonstrate the potential of complementary authority routing to sustain successful manipulation with substantially reduced dependence on continuous human control.