CS2125 Paper Review Form - Winter 2019

Reviewer: Abdul Kawsar Tushar

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, Jungsuk Kwac, Wendy Ju, Martin Steinert, Larry Leifer, and Clifford Nass

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
 [ ] 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)

An interesting aspect of car-driver interaction, namely the impact of message relays from the car on the mindset of the driver, was explored in this paper. The research suggests that there is an optimal level where the amount of 'why' and 'how' information lead to the safest and most satisfied driving experience. The authors suggested more research to know about this level of optimality, preferably in real life driving conditions. This paper is one of the first to explore explanation message relaying service before an action is taken, in contrast with previous other studies which convey the message after an action is taken.

This paper looks at human side of the automated driving vehicle message relaying system and thus methodically novel. Thus, it has good significance.


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

S1 - This paper is one of the first to explore explanation message relaying service before an action is taken.

S2 - The researchers had access to a prototype which simulates the real-life driving scenarios in a self-driving car, which enabled them to help the participants assess the practical situations more correctly.


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

W1 - The time required to explain an imminent action to be taken by the system needs some time. I am not sure how much time will be available for explanation in certain scenarios, especially if some of the possible options result in potentially hazardous conditions.

W2 - The model of car-driver message relay was generalized for all humans, without regard to the condition/mentality of the driver. All the persons are not the same and do not have the same mental capability, and this difference needs to be incorporated in the model in some capacity for better adjustment on a personal level.

W3 - More connection to the existing literature is welcome. Specifically, how the findings of this study connect to the outcomes of previous studies as well as empirical results was not elaborated upon. Moreover, similar settings could be observed in other automated ecosystems, for example in machine operation scenarios or airplane autopilot in certain cases. Studies from those areas could be used to compare and validate.