The Impact of Autonomy Levels and System Errors on Cognitive Load and Trust in Human-Robot Collaborative Tasks

Abstract

Trust plays a crucial role in user performance during collaborative human-robot interaction. This study examines how varying levels of autonomy and system errors affect user trust and cognitive load in collaborative tasks between robots and humans. Participants performed a collaborative task using a UR5 robotic arm to place four bottles of different shapes into a box within a three-minute time frame under three conditions: (C1) full manual control by the user, (C2) autonomous operation with few errors—where the robot fails to correctly place one out of four bottles and the user can intervene upon detecting failures, and (C3) autonomous operation with frequent errors—where the robot fails to correctly place three out of four bottles, with user intervention allowed upon failure detection. Physiological indicators such as blink rate, galvanic skin response (GSR), and facial temperature, along with task performance metrics such as success rate and completion time were tracked. The results showed that participants experienced the highest cognitive load in Condition 1, as indicated by higher NASA-TLX scores, increased blink rates (average of 65 blinks per minute), elevated facial temperatures, and higher GSR readings. Trust levels were lowest in Condition 3, with 74% of participants reporting low trust, highlighting the significant impact of robot reliability on user’s trust. A strong negative correlation was found between cognitive load and trust in Condition 3 suggesting that increased cognitive load due to frequent robot errors leads to decreased trust. These findings contribute to understanding how system errors and autonomy levels influence cognitive load and trust in collaborative human-robot tasks. The insights gained can inform the design of collaborative robotic systems that balance autonomy and reliability, enhancing user experience and performance.