Including the Human in On-Demand Autonomy

Source Organization:
Principal Investigator:Raj Rajkumar
PI Contact
Project Manager:
Funding Source(s) and Amounts Provided (by each agency or organization):
Total Dollars:$50,000
Agency ID/Contract/Grant Number:
Start and End Dates:
Project Status:Complete
Subject Categories:safety and human factors
Abstract:Our project goal is to study how a human driver and a vehicle equipped with ADAS can interact and make driving safer. The General Motors-CMU Autonomous Driving Collaborative Research Laboratory at CMU has developed an autonomous 2011 Cadillac SRX (shown). Full autonomy will eventually lead to significant reductions in accidents, injuries and fatalities. In the interim, the human driver will be in the loop even if the vehicle is semi-autonomous (as in cruise control and adaptive cruise control) or occasionally autonomous “on-demand” (as in automatic parallel parking). Driver-friendly (visual, aural and tactile) alerts will be generated based on the severity of obstacles in the environment detected by the fusion of varied sensory inputs. In cluttered environments, bad weather, and poor road conditions, the vehicle will warn the user to take control and also attempt to enforce a lower speed on the vehicle. Proper configurations and policies will need to be defined. The driver must also be able to seamlessly switch back and forth between autonomous and manual driving modes.
Describe Implementation of Research Outcomes (or why not implemented):
Impacts/Benefits of Implementation (actual, not anticipated):
Project URL: