Table 1. Comparison of breach detection and enforcement.
| Case 1: Static robot no occlusions | |||
| Metric | CCTV-only | Robot-only | Robot-CCTV Hybrid |
| Number of breaches detected | 20 | 10 | 30 |
| Number of enforcements | NA | 10 | 30 |
| Case 2: Static robot with 50% occlusion | |||
| Number of breaches detected | 20 | 7 | 27 |
| Number of enforcements | NA | 7 | 27 |
| Case 3: Static robot with >50% occlusion | |||
| Number of breaches detected | 20 | 3 | 23 |
| Number of enforcements | NA | 3 | 23 |
| Case 4: Lawnmower exploration with 50% occlusions | |||
| Number of breaches detected | 20 | 20 | 40 |
| Number of enforcements | NA | 20 | 40 |
| Case 5: Lawnmower exploration with >50% occlusions | |||
| Number of breaches detected | 20 | 20 | 40 |
| Number of enforcements | NA | 20 | 40 |
Comparison of three configurations in terms of detecting breaches in social distancing norms when two pedestrians are static in any one of 40 points in a laboratory setting. We observe that CCTV+robot configuration has the most number of breaches detected even when the robot is static and outside the CCTV’s sensing range. When the robot is following lawnmower waypoints outside of the CCTV’s FOV, it can detect a breach in any of the 20 locations that could not be detected by the CCTV camera, even with high levels of occlusion.