Design of Proactive Interaction for In-Vehicle Robots Based on Transparency

Area of Science:

• Human-computer interaction
• Automotive safety
• Artificial intelligence in vehicles

Background:

• Transparency theory is crucial for understanding human-robot interaction.
• In-vehicle robots require clear communication for safe and effective operation.
• Proactive interaction design in vehicles is an emerging field.

Purpose of the Study:

• To determine the optimal amount of transparency information for in-vehicle robots.
• To evaluate transparency levels across voice and visual channels in proactive scenarios.
• To assess the impact of transparency on driver safety, usability, trust, and emotion.

Main Methods:

• Utilized a driving simulator to conduct experiments.
• Collected both subjective and objective data from drivers.
• Tested various transparency levels and channel combinations for in-vehicle robots.

Main Results:

• Appropriate transparency expression significantly improved drivers' driving control.
• Subjective evaluations by drivers were enhanced through adequate transparency.
• The amount of transparency needed varies based on the type of driving task.

Conclusions:

• Optimizing in-vehicle robot transparency is key to improving driver experience and safety.
• Tailoring transparency to specific tasks enhances human-robot collaboration in driving.
• Further research into proactive interaction design can lead to safer autonomous systems.