CS2125 Paper Review Form - Winter 2019

Reviewer: Abdul Kawsar Tushar

Paper Title: Autonomous Vehicle Safety: An Interdisciplinary Challenge

Author(s): Philip Koopman and Michael Wagner

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

2) Originality
 [ ] Very good (very novel, trailblazing work)
 [ ] Good 
 [ ] Marginal (very incremental)
 [X] 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
 [ ] Significant
 [X] 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)

A nice paper that outlines the broad areas that need to be examined in order for ensuring reasonable safety thresholds of any self-driving vehicle. The fields of my interest here are human-computer interaction and social acceptance; however, the paper also talks about the reliability of software & hardware systems, testing & security, and legal & ethical challenges. There are papers that inspect one or some of these areas, but when we are presented with such a broad picture as in this paper, we start to get some feel of how vast the challenge actually is when it comes to deploying self-driving cars with reasonable safety on the roads. The paper emphasizes the importance of establishing clear guidelines in numerous areas before a fully automated vehicle or a sufficient number of semi-automated vehicles could ply on the roads.

This paper sumamrizes the previous researches and poses some interesting open questions. The strength of this paper in its fluidity and clarity. Although this paper does not have much novel or significant work itself, it works well as a starting point for research on autonomous driving vehicles.



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

S1 - The paper correctly aligns itself with the SAE J3016 Levels of Automation and ADS hazard sources taught in the lectures.

S2 - Having to summarize large areas of research within half a page each is a daunting task and the authors do this job admirably.

S3 - This paper was not intended to be a technical and inscrutable paper, rather the aim was to give an abstract overview with enough case study questions and examples. In this regard, the paper is fairly successful.


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

W1 - When a paper is dealing with such a broad array of topics, it is difficult to focus equally on all areas. The security part could have received more attention.

W2 - The focus on car-driver interaction is a major point of discussion as a part of safety in autonomous vehicles. This section could have included some more background and references. A point that this section seems to ignore is the seeming irrationality that other car drivers sometimes tend to exhibit and how to deal with this human irrationality portion to ensure the safety of the automated car and its passengers.

W3 - This paper does not propose anything new; in some sense, this is a review paper.