CS2125 Paper Review Form - Winter 2019

Reviewer: Hazem Ibrahim

Paper Title: Why did my car just do that? Explaining semi-autonomous driving actions to improve driver understanding, trust, and performance.

Author(s): Jeamin Koo, Junsuk Kwac, Wendy Ju, Martin Steinert, Larry Leifer, Clifford Nass

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)
 [ ] Accept (high quality - would argue for acceptance)
 [X] 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 explores the presentation and context of delivering information to the driver in semi-autonomous vehicles. The authors tackle the situation of auto-braking functionality in a semi-autonomous driving system, and observe the reaction of participants when presented with two different types of messages accompanying the auto-braking action. Firstly, they tackled "how" messages, which explain what action the car is about to take (e.g "Car is braking"). Secondly, they introduce "why" messages, which explain why the car is taking an action (e.g "Obstacle ahead"). The authors also tested for combinations of these messages. Results from the paper indicated that participants preferred the "why" messages, however the safest driving behaviour was observed for a combination of both the "how" and "why" messages.

While the paper suffers from a number of weaknesses listed below, I would weakly argue for it's acceptance as at the time of its publishing, it introduced an interesting result with regards to the types of messages delivered to the user, which was later utilized in a number of other studies which had cited this paper.



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

S1. Good introduction to the field of car-driver handoff and driver emotional responses to messages.

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

W1. Statistical measure to determine safe driving performance was not elaborated on and did not seem rigorous.
W2. Study did not employ a diverse set of participants, which may lead to designs that only fit a specfic group of the population.