{ "id": 251044, "title": "Has anyone calculated the same pseudorange numbers between RINEX, GnssLog and _derived?", "url": "/competitions/google-smartphone-decimeter-challenge/discussion/251044", "author_name": "", "post_date": "2021-07-05T16:20:29.013436600Z", "votes": 10, "comment_count": 5, "views": 0, "content": "

I'm trying to match up the raw pseudorange numbers between the RINEX, GnssLog and _derived files, but keep getting different answers:

\n

In the pdf here https://www.kaggle.com/google/android-smartphones-high-accuracy-datasets?select=ION+GNSS+2020+Android+Raw+GNSS+Measurement+Datasets+for+Precise+Positioning.pdf it talks about how RINEX has a 100 nanosecond limitation (the times have to be floored to 100ns to fit in the RINEX format), so I expected that to be different, but I still can't get GnssLog computations to match the _derived file

\n

In that same pdf it talks about using Doppler to adjust the range so I'm guessing that's the part I'm missing - but still haven't been able to match GnssLog calculated pseudorange to the _derived pseudoranges (I seem to be off by 4m - 40m)

\n

Has anyone been able to successfully calculate the range from GnssLog and match it to the _derived.csv values?

", "messages": [ { "id": "1377173", "postDate": "07/05/2021 16:20:29", "content": "

I'm trying to match up the raw pseudorange numbers between the RINEX, GnssLog and _derived files, but keep getting different answers:

\n

In the pdf here https://www.kaggle.com/google/android-smartphones-high-accuracy-datasets?select=ION+GNSS+2020+Android+Raw+GNSS+Measurement+Datasets+for+Precise+Positioning.pdf it talks about how RINEX has a 100 nanosecond limitation (the times have to be floored to 100ns to fit in the RINEX format), so I expected that to be different, but I still can't get GnssLog computations to match the _derived file

\n

In that same pdf it talks about using Doppler to adjust the range so I'm guessing that's the part I'm missing - but still haven't been able to match GnssLog calculated pseudorange to the _derived pseudoranges (I seem to be off by 4m - 40m)

\n

Has anyone been able to successfully calculate the range from GnssLog and match it to the _derived.csv values?

", "rawMarkdown": "I'm trying to match up the raw pseudorange numbers between the RINEX, GnssLog and _derived files, but keep getting different answers:\n\nIn the pdf here https://www.kaggle.com/google/android-smartphones-high-accuracy-datasets?select=ION+GNSS+2020+Android+Raw+GNSS+Measurement+Datasets+for+Precise+Positioning.pdf it talks about how RINEX has a 100 nanosecond limitation (the times have to be floored to 100ns to fit in the RINEX format), so I expected that to be different, but I still can't get GnssLog computations to match the _derived file\n\nIn that same pdf it talks about using Doppler to adjust the range so I'm guessing that's the part I'm missing - but still haven't been able to match GnssLog calculated pseudorange to the _derived pseudoranges (I seem to be off by 4m - 40m)\n\nHas anyone been able to successfully calculate the range from GnssLog and match it to the _derived.csv values?", "votes": null }, { "id": "1377194", "postDate": "07/05/2021 16:41:44", "content": "

Ah! (duh), the epoch timestamp is different than the received timestamp, so the doppler (PseudorangeRateMetersPerSecond) has to be used to adjust for that.

\n

I'm still getting ~4m difference, but I'm matching the RINEX file now, which I think means I'm into decimal rounding errors of my program and have to adjust something there perhaps.

", "rawMarkdown": "Ah! (duh), the epoch timestamp is different than the received timestamp, so the doppler (PseudorangeRateMetersPerSecond) has to be used to adjust for that.\n\nI'm still getting ~4m difference, but I'm matching the RINEX file now, which I think means I'm into decimal rounding errors of my program and have to adjust something there perhaps.", "votes": null }, { "id": "1379645", "postDate": "07/07/2021 14:03:13", "content": "

Hi Chris,

\n

Were you able to generate a solution file based only on derived.csv file ? I'm not able to generate requisite number of rows(91486) for successful submission. It seems that the data is missing in derived.csv file compared to the corresponding rinex observation file.

\n

Any insights will be helpful.

\n

Thanks.

", "rawMarkdown": "Hi Chris,\n\nWere you able to generate a solution file based only on derived.csv file ? I'm not able to generate requisite number of rows(91486) for successful submission. It seems that the data is missing in derived.csv file compared to the corresponding rinex observation file.\n\nAny insights will be helpful.\n\nThanks.", "votes": null }, { "id": "1380165", "postDate": "07/07/2021 21:49:02", "content": "

I also had trouble matching up 100% of points - what I ended up doing is used the baseline csv lat/long values in the places where I couldn't match it all up.

\n

It's not ideal, but it seemed to be just a few points per run, so I figured it would be ok. I haven't fully investigated why or where the missing rows are though - it's possible the data is there but mislabeled, or off by just a bit or something like that; I'm not sure.

", "rawMarkdown": "I also had trouble matching up 100% of points - what I ended up doing is used the baseline csv lat/long values in the places where I couldn't match it all up.\n\nIt's not ideal, but it seemed to be just a few points per run, so I figured it would be ok. I haven't fully investigated why or where the missing rows are though - it's possible the data is there but mislabeled, or off by just a bit or something like that; I'm not sure.", "votes": null }, { "id": "1380886", "postDate": "07/08/2021 12:07:07", "content": "

Thanks for letting me know Chris.

\n

According to my calculations, it seems there are some 2000 epochs, considering all the derived.csv belonging to test data folder, for which data is missing when compared to corresponding Rinex observation files.

", "rawMarkdown": "Thanks for letting me know Chris.\n\nAccording to my calculations, it seems there are some 2000 epochs, considering all the derived.csv belonging to test data folder, for which data is missing when compared to corresponding Rinex observation files.", "votes": null }, { "id": "1381847", "postDate": "07/09/2021 09:21:25", "content": "

Ok yes, I'm seeing the same (about ~2200). hm. I'll have to look into that further to see what might be going on…

", "rawMarkdown": "Ok yes, I'm seeing the same (about ~2200). hm. I'll have to look into that further to see what might be going on...", "votes": null } ], "comments": [ { "id": 1377194, "author_name": "chris62", "author_url": "", "post_date": "07/05/2021 16:41:44", "content": "

Ah! (duh), the epoch timestamp is different than the received timestamp, so the doppler (PseudorangeRateMetersPerSecond) has to be used to adjust for that.

\n

I'm still getting ~4m difference, but I'm matching the RINEX file now, which I think means I'm into decimal rounding errors of my program and have to adjust something there perhaps.

", "votes": null, "replies": [] }, { "id": 1379645, "author_name": "naman4u13", "author_url": "", "post_date": "07/07/2021 14:03:13", "content": "

Hi Chris,

\n

Were you able to generate a solution file based only on derived.csv file ? I'm not able to generate requisite number of rows(91486) for successful submission. It seems that the data is missing in derived.csv file compared to the corresponding rinex observation file.

\n

Any insights will be helpful.

\n

Thanks.

", "votes": null, "replies": [ { "id": 1380165, "author_name": "chris62", "author_url": "", "post_date": "07/07/2021 21:49:02", "content": "

I also had trouble matching up 100% of points - what I ended up doing is used the baseline csv lat/long values in the places where I couldn't match it all up.

\n

It's not ideal, but it seemed to be just a few points per run, so I figured it would be ok. I haven't fully investigated why or where the missing rows are though - it's possible the data is there but mislabeled, or off by just a bit or something like that; I'm not sure.

", "votes": null, "replies": [] }, { "id": 1380886, "author_name": "naman4u13", "author_url": "", "post_date": "07/08/2021 12:07:07", "content": "

Thanks for letting me know Chris.

\n

According to my calculations, it seems there are some 2000 epochs, considering all the derived.csv belonging to test data folder, for which data is missing when compared to corresponding Rinex observation files.

", "votes": null, "replies": [] }, { "id": 1381847, "author_name": "chris62", "author_url": "", "post_date": "07/09/2021 09:21:25", "content": "

Ok yes, I'm seeing the same (about ~2200). hm. I'll have to look into that further to see what might be going on…

", "votes": null, "replies": [] } ] } ], "raw_markdown_by_id": { "1377173": "I'm trying to match up the raw pseudorange numbers between the RINEX, GnssLog and _derived files, but keep getting different answers:\n\nIn the pdf here https://www.kaggle.com/google/android-smartphones-high-accuracy-datasets?select=ION+GNSS+2020+Android+Raw+GNSS+Measurement+Datasets+for+Precise+Positioning.pdf it talks about how RINEX has a 100 nanosecond limitation (the times have to be floored to 100ns to fit in the RINEX format), so I expected that to be different, but I still can't get GnssLog computations to match the _derived file\n\nIn that same pdf it talks about using Doppler to adjust the range so I'm guessing that's the part I'm missing - but still haven't been able to match GnssLog calculated pseudorange to the _derived pseudoranges (I seem to be off by 4m - 40m)\n\nHas anyone been able to successfully calculate the range from GnssLog and match it to the _derived.csv values?", "1377194": "Ah! (duh), the epoch timestamp is different than the received timestamp, so the doppler (PseudorangeRateMetersPerSecond) has to be used to adjust for that.\n\nI'm still getting ~4m difference, but I'm matching the RINEX file now, which I think means I'm into decimal rounding errors of my program and have to adjust something there perhaps.", "1379645": "Hi Chris,\n\nWere you able to generate a solution file based only on derived.csv file ? I'm not able to generate requisite number of rows(91486) for successful submission. It seems that the data is missing in derived.csv file compared to the corresponding rinex observation file.\n\nAny insights will be helpful.\n\nThanks.", "1380165": "I also had trouble matching up 100% of points - what I ended up doing is used the baseline csv lat/long values in the places where I couldn't match it all up.\n\nIt's not ideal, but it seemed to be just a few points per run, so I figured it would be ok. I haven't fully investigated why or where the missing rows are though - it's possible the data is there but mislabeled, or off by just a bit or something like that; I'm not sure.", "1380886": "Thanks for letting me know Chris.\n\nAccording to my calculations, it seems there are some 2000 epochs, considering all the derived.csv belonging to test data folder, for which data is missing when compared to corresponding Rinex observation files.", "1381847": "Ok yes, I'm seeing the same (about ~2200). hm. I'll have to look into that further to see what might be going on..." }, "source": "meta" }