Test visualisation tool
A computer system for rendering a graphical user interface for visualising runs of a driving scenario in which an ego agent navigates a road layout, comprising an input configured to receive a map of the road layout and run data comprising a sequence of timestamped ego agent states and a time-varying numerical score quantifying the performance of the ego agent with respect a set of run evaluation rules; and a rendering component configured to cause a graphical user interface to display, for each rule: a plot of the time-varying numerical score, and a marker denoting a selected time index of the plot, the marker movable along the time axis to change the selected time index; and a scenario visualization comprising a visualization of the run at the selected time index, whereby moving the marker along the time axis causes the scenario visualisation to update as the time index is changed.
1 . A computer system for rendering a graphical user interface for visualising runs of a driving scenario in which an ego agent navigates a road layout, the computer system comprising:
at least one memory storing computer-readable instructions; and
at least one processor coupled to the at least one memory and configured to execute the computer-readable instructions, which upon execution cause the at least one processor to:
receive a map of the road layout of the driving scenario and run data of a run of the driving scenario, wherein the run data comprises:
a sequence of timestamped ego agent states, and
a time-varying numerical score quantifying performance of the ego agent with respect to each rule of a set of run evaluation rules, computed by applying the run evaluation rule to the run; and
generate rendering data for causing a graphical user interface to display:
for each rule of the run evaluation rules:
a plot of the time-varying numerical score, and
a marker denoting a selected time index on a time axis of the plot, the marker being movable along the time axis via user input at the graphical user interface to change the selected time index, and
a scenario visualization comprising a visualization of the road layout, overlaid with an agent visualization of the run at the selected time index, whereby moving the marker along the time axis causes the at least one processor to update the scenario visualisation as the selected time index is changed.
2 . The computer system of claim 1 , wherein the run is a first run, and wherein the at least one processor is further configured to receive second run data of a second run of the driving scenario, the second run data comprising a second sequence of timestamped ego agent states and a second time-varying numerical score quantifying a performance of the ego agent with respect to each rule of a set of run evaluation rules, computed by applying the run evaluation rule to the run; and wherein the at least one processor is further configured to generate rendering data for causing a graphical interface to display, for each rule of the set of run evaluation rules:
a plot of the second time-varying numerical score, wherein the time-varying numerical score and the second time-varying numerical score are plotted with respect to a common set of axes comprising at least a common time axis, wherein the marker denotes a selected time index on the common time axis, and
a second agent visualisation of the second run at the selected time index, wherein the scenario visualisation is overlaid with the second agent visualisation.
3 . The computer system of claim 1 , wherein the time-varying numerical score is computed by applying one or more rules to time-varying signals extracted from the run data, and wherein changes in the signals are visible in the scenario visualisation.
4 . The computer system of claim 2 , wherein the at least one processor is configured, responsive to a deselection input at the graphic user interface denoting one of the first and second runs, to:
for each driving rule, remove the plot of the time-varying numerical score of the deselected run from the common set of axes, and
remove the agent visualization of the deselected run from the visualization of the road layout,
whereby a user can switch from a run-comparison view pertaining to both of the first and second runs to a single-run view pertaining to only one of the first and second runs.
5 . The computer system of claim 2 , wherein the graphical user interface additionally includes a comparison table having an entry for each rule of the set of run evaluation rules, the entry containing an aggregate performance result for that rule in the first run and an aggregate performance result for that rule in the second run.
6 . The computer system of claim 5 , wherein the entry for each rule additionally comprises a description of that rule.
7 . The computer system of claim 1 , wherein the at least one processor is configured to, in response to an expansion input at the graphical user interface, hide the plot of the time-varying numerical scores for each rule and display a timeline view comprising an indication of a pass/fail result of the rule over time.
8 . The computer system of claim 1 , wherein the at least one processor is configured to cause the graphical user interface to display, for each rule of the set of run evaluation rules, the numerical score at the selected time index.
9 . The computer system of claim 1 , wherein the run evaluation rules comprise perception rules and wherein the scenario visualisation comprises a set of perception outputs generated by a perception component of the ego agent.
10 . The computer system of claim 9 , wherein the scenario visualisation comprises sensor data overlaid on the visualisation of the road layout.
11 . The computer system of claim 1 , wherein the scenario visualisation comprises a scenario time line having a scenario time marker, whereby moving the marker along the scenario time line causes the at least one processor to update the respective time marker of each plot of the time-varying numerical score as the selected time index is changed.
12 . The computer system of claim 11 , wherein the scenario time line comprises a frame index corresponding to the selected time index and a set of controls to move forwards or backwards by respectively incrementing or decreasing the frame index.
13 . The computer system of claim 1 , wherein the driving scenario is a simulated driving scenario in which a simulated ego agent navigates a simulated road layout, and wherein the run data is received from a simulator.
14 . The computer system of claim 1 , wherein the driving scenario is a real-world driving scenario in which an ego agent navigates a real-world road layout, and wherein the run data is computed based on data generated on board the ego agent during the run.
15 . The computer system of claim 1 , wherein the plot of the time-varying numerical score comprises an xy-plot of the time-varying numerical score.
16 . The computer system of claim 1 , wherein the time-varying numerical score is plotted using colour coding.
17 . A method for visualising runs of a driving scenario in which an ego agent navigates a road layout, the method comprising:
receiving a map of the road layout of the driving scenario and run data of a run of the driving scenario, wherein the run data comprises:
a sequence of timestamped ego agent states,
a time-varying numerical score quantifying performance of the ego agent with respect to each rule of a set of run evaluation rules, computed by applying the run evaluation rule to the run,
generate rendering data for causing a graphical user interface to display:
for each rule of the run evaluation rules:
a plot of the time-varying numerical score, and
a marker denoting a selected time index on a time axis of the plot, the marker being movable along the time axis via user input at the graphical user interface to change the selected time index, and
a scenario visualization comprising a visualization of the road layout, overlaid with an agent visualization of the run at the selected time index, whereby moving the marker along the time axis causes an update to the scenario visualization as the selected time index is changed.
18 . A non-transitory computer readable medium embodying computer program instructions, the computer program instructions configured so as, when executed on one or more hardware processors, to implement operations comprising:
receiving a map of a road layout of a driving scenario and run data of a run of the driving scenario, wherein the run data comprises:
a sequence of timestamped ego agent states,
a time-varying numerical score quantifying performance of the ego agent with respect to each rule of a set of run evaluation rules, computed by applying the run evaluation rule to the run,
generate rendering data for causing a graphical user interface to display:
for each rule of the run evaluation rules:
a plot of the time-varying numerical score, and
a marker denoting a selected time index on a time axis of the plot, the marker being movable along the time axis via user input at the graphical user interface to change the selected time index, and
a scenario visualization comprising a visualization of the road layout, overlaid with an agent visualization of the run at the selected time index, whereby moving the marker along the time axis causes the computer program instructions to update the scenario visualization as the selected time index is changed.
19 . The non-transitory computer readable medium of claim 18 , wherein the computer program instructions are further configured, when executed on the one or more hardware processors, to receive second run data of a second run of the driving scenario, the second run data comprising a second sequence of timestamped ego agent states and a second time-varying numerical score quantifying a performance of the ego agent with respect to each rule of a set of run evaluation rules, computed by applying the run evaluation rule to the run; and wherein the computer program instructions are further configured to generate rendering data for causing a graphical interface to display, for each rule of the set of run evaluation rules:
a plot of the second time-varying numerical score, wherein the time-varying numerical score and the second time-varying numerical score are plotted with respect to a common set of axes comprising at least a common time axis, wherein the marker denotes a selected time index on the common time axis, and
a second agent visualisation of the second run at the selected time index, wherein the scenario visualisation is overlaid with the second agent visualisation.
20 . The non-transitory computer readable medium of claim 18 , wherein the time-varying numerical score is computed by applying one or more rules to time-varying signals extracted from the run data, and wherein changes in the signals are visible in the scenario visualization.