CS2125 Paper Review Form - Winter 2019

Reviewer: Eric Langlois

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?
 [X] Yes
 [ ] 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)
 [X] Good (comparable to typical conference papers)
 [ ] Marginal depth
 [ ] Little or no depth

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

5) Presentation
 [X] Very well written
 [ ] 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)

The authors propose the use of cooperative interfaces for autonomous driving in
which the vehicle may query the driver for guidance without disengaging to
manual control (this does not appear to be an original proposal).
They conduct a user study of various cooperative interfaces to a simulated
autonomous vehicle encountering a stopped car blocking the road. The study
results indicate, among other things, that cooperative interfaces are
a promising approach for responsible user guidance and that such interfaces
should be kept simple and straightforward.

I recommend that the paper be accepted because of its meaningful contribution,
well-designed study, thorough description of the experiment and results, and
insightful discussion. However, the experiment is small and does not support
strong conclusions so the potential impact of this work is limited.

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

S1 The study seems to be well-designed and addresses multiple relevant factors:
  environment complexity, number of available options, interaction modality, and
  whether suggested options are legal.

S2 The authors provide an informative analysis of the study results and
  participant feedback.

S3 The discussion section is insightful and well-written. The authors fairly
  discuss the scope and limitations of the study.

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

W1 Some of the participant feedback does not seem meaningful without any
  comparison (interaction ease / stressfulness, trust, performance).

W2 How much of the driver time was spent interacting with the system versus
  analyzing the scenario and deciding on an action?

W3 Given the unrealistic human-emulated voice recognition, I don't think that
  one can confidently conclude that "voice input is a good interaction
  modality", merely that it could be if the voice recognition had high fidelity.
  The criticism applies only to this specific part of the conclusion as the rest
  of the paper is clear about the use of human voice recognition and its
  implications.