Research map / Multi-agent systems and games / Games and equilibria
Improving Surveillance Using Cooperative Target Observation
Rashi Aswani, Sai Krishna Munnangi, Praveen Paruchuri
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| set alpha to 1 instead of 0.25 or small values (ablation) | k-means style observer · 18 observers, 3/9/15 targets | avg targets observed: 4.39 -> 6.82 | Improved |
| use 0-1 weight model instead of 0-.5-1 model (ablation) | Explore-Exploit observer · 10 observers, 3-27 targets | mean targets observed: 1.76 -> 2.3 (3 targets); 10.9 -> 11.47 (27 targets) | Improved |
| 0-1 model versus Model 3 (ablation) | Explore-Exploit observer · 10 observers, 3-27 targets | mean targets observed: 2.21 -> 2.3 | Improved |
| target controlled randomization mix 70-30 versus 50-50 (ablation) | target strategy · 10 observers, 27 targets | mean targets observed (lower better for targets): 11.93 -> 11.62 | Improved |
| targets use straight-line movement instead of random | targets · sensor 15, speeds 0.5-1.2 | targets observed | Improved |
| controlled randomization instead of purely random target movement | targets · sensor 15, speeds 0.5-1.2 | targets observed | Improved |
| add randomness to straight-line target movement | targets · sensor 15 | targets observed | Hurt |
| memorization observer versus Explore-Exploit | Explore-Exploit · controlled randomization targets | targets observed | Mixed |
| one-step prediction versus Explore-Exploit | Explore-Exploit · controlled randomization targets | targets observed | No clear effect |
| k-step prediction versus Explore-Exploit | Explore-Exploit · controlled randomization targets | targets observed | Improved |
| raise reward threshold in BRLP-CTO from 50% to 100% of optimal (ablation) | BRLP-CTO · sensor 15, speeds 0.8/1.2 | average entropy: 3.321 -> 2.137 | Hurt |
Closest papers by meaning
- Distributed Multi-Target Tracking and Data Association in Vision Networks (TPAMI 2016 · similarity 0.82)
- Learning Multi-Agent Coordination for Enhancing Target Coverage in Directional Sensor Networks (NeurIPS 2020 · similarity 0.81)
- MATE: Benchmarking Multi-Agent Reinforcement Learning in Distributed Target Coverage Control (NeurIPS 2022 · similarity 0.81)
- Target Surveillance in Adversarial Environments Using POMDPs (AAAI 2016 · similarity 0.81)
- Multi-Objective Multi-Agent Planning for Jointly Discovering and Tracking Mobile Objects (AAAI 2020 · similarity 0.81)
- CP-Guard: Malicious Agent Detection and Defense in Collaborative Bird’s Eye View Perception (AAAI 2025 · similarity 0.79)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
