CS2125 Paper Review Form - Winter 2019

Reviewer: Hazem Ibrahim	

Paper Title: Towards Cooperative Driving: Involving the Driver in an Autonomous Vehicle's Decision Making

Author(s): Marcel Walch, Tobias Sieber, Philipp Hock, Martin Baumann, Michael Weber

1) Is the paper technically correct?
 [ ] Yes
 [X] Mostly (minor flaws, but mostly solid)
 [ ] No

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [X] Good 
 [ ] Marginal (very incremental)
 [ ] Poor (little or nothing that is new)

3) Technical Depth
 [ ] Very good (comparable to best conference papers)
 [ ] Good (comparable to typical conference papers)
 [X] Marginal depth
 [ ] Little or no depth

4) Impact/Significance
 [ ] Very significant
 [X] Significant
 [ ] Marginal significance.
 [ ] Little or no significance.

5) Presentation
 [ ] Very well written
 [X] Generally well written
 [ ] Readable
 [ ] Needs considerable work
 [ ] Unacceptably bad

6) Overall Rating
 [ ] Strong accept (award quality)
 [X] Accept (high quality - would argue for acceptance)
 [ ] Weak Accept (borderline, but lean towards acceptance)
 [ ] Weak Reject (not sure why this paper was published)


7) Summary of the paper's main contribution and rationale
   for your recommendation. (1-2 paragraphs)

This paper introduces an interesting solution to mitigating vehicle to driver handoff in autonomous driving systems through the use of cooperative interfaces. The authors suggest that in a situation where the vehcile is uncertain of how to proceed, for example in the case of a blocked lane, the vehicle can propose a set of solutions which the driver may select from. The driver then must evaluate the solutions presented, and decice to either proceed with one of the solutions or manually take over control of the vehicle. The solutions assessed by the system were presented to the driver both visually in the form of options of a screen and verbally. The driver can either respond verbally by selection one of the options or by touching an option on the touchscreen. Through the experiment, the authors had several key findings. They noted that most participants acted responsibly through thorough assessment of the solution presented by the vehicle before selecting an option to proceed. However, in some scenarios, the driver misinterepreted one of the signs shown in the simulation, which caused them to select an option which violated the traffic regulations, and hence, the vehicle should help drivers perceive and assess traffic situations by highlighting road signs. Finally, they noted that in many instances, which the speec recognition system operated without fault, many users tended to mistrust speech recognition due to a perceived lack of robustness when compared with selecting an option on the touchscreen.

Overall, the paper presented some incrimental work towards enhancing the driver-vehicle interaction in autonomous driving cars, with the possibility for building upon the ideas presented in the future, and hence I would argue for it's acceptance.


8) List 1-3 strengths of the paper.  (1-2 sentences each,
identified as S1, S2, S3.)

S1. The paper was generally well-written and easy to follow and understand.

S2. The paper acknowledges it's limitations clearly and states that it should be taken as a starting point for future research rather than as a comprehensive study.


9) List 1-3 weaknesses of the paper (1-2 sentences each,
identified as W1, W2, W3.)

W1. The authors of this paper only provided a mean age for their participant pool but they did not provide an age range. In any study surrounding autonomous driving systems, the participant pool should be representative of potential users of an autonomous driving system.

W2. Figure 7 was incredibly hard to understand. I was not sure what information I was supposed to be gaining by reading the figure. 

W3. The reward system mentioned was not elaborated on even though it was made to be the final point in the "Discussion" section.