CS2125 Paper Review Form - Winter 2019

Reviewer: Eric Langlois

Paper Title: 
Springrobot: A Prototype Autonomous Vehicle
and Its Algorithms for Lane Detection

Author(s): Qing Li, Nanning Zheng, and Hong Cheng

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
 [ ] Generally well written
 [X] 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 describe the "Springrobot" autonomous car architecture and propose
the Adaptive Randomized Hough Transform (ARHT) algorithm for lane detection. The
ARHT algorithm is at its core a Hough Transform (a geometric shape
identification algorithm) that is tailored for lane marking curves and modified
in several ways for efficiency. My acceptance of the paper is based on the
development and description of this algorithm. It is presented clearly, the
design is motivated well, and it appears to be a useful contribution.
Unfortunately, the paper lacks any empirical testing of the algorithm; the tests
are limited to several example lane predictions (including some errors). This
paper would be improved if the authors included empirical tests of the
algorithms efficiency and accuracy compared to other methods.


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

S1: The ARHT algorithm is described comprehensively. The design
decisions are motivated well.

S2: The described ARHT appears to be a good contribution for efficient lane
detection, although it is difficult to say this confidently without empirical
study.

S3: The background on lane detection is broad and informative. The other
techniques are described at an appropriate level of detail.


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

W1: The experiment section lacks any empirical study of the algorithm. I would
like to see statistics on the performance and accuracy of their proposed method
and comparisons against other possible algorithms.

W2: The paper lacks focus: part is concerned with the architecture of the
Springrobot system and part is about the ARHT algorithm.

W3: The system architecture diagrams are interesting but lack context and
description in the main paper text.