PRoID: Predicted Rate of Information Delivery in Multi-Robot Exploration and Relaying
Authors: Seungchan Kim, Seungjae Baek, Micah Corah, Graeme Best, Brady Moon, Sebastian Scherer
Organizations: Carnegie Mellon University Robotics Institute · Ulsan National Institute of Science & Technology · Colorado School of Mines · University of Technology Sydney · Brigham Young University
We address Multi-Robot Exploration and Relaying (MRER): a team of robots must explore an unknown environment and deliver acquired information to a fixed base station within a mission time limit. The central challenge is deciding when each robot should stop exploring and relay: this depends on what the robot is likely to find ahead, what information it uniquely holds, and whether immediate or future delivery is more valuable. Prior approaches either ignore the reporting requirement entirely or rely on fixed-schedule relay strategies that cannot adapt to environment structure, team composition, or mission progress. We introduce PRoID (Predicted Rate of Information Delivery), a relay criterion that uses learned map prediction to estimate each robot's future information gain along its planned path, accounting for what teammates are already relaying. PRoID triggers relay when immediate return yields higher information delivery per unit time. We further propose PRoID-Safe, a failure-aware extension that incorporates robot survival probability into the relay criterion, naturally biasing decisions toward earlier relay as failure risk grows. We evaluate on real-world indoor floor plan datasets and show that PRoID and PRoID-Safe outperform fixed-schedule baselines, with stronger relative gains in failure scenarios.
Figures & tables
Fig. 1: Multi-robot exploration must not only cover unknown environments but also deliver collected information to a base station in time. PRoID enables adaptive relay decisions by comparing each robot’s current observed coverage against its predicted future sensor coverage along the planned path.
Fig. 2: Overview of PRoID : robots explore unknown environments and share map data when in range. Each robot tracks its unique unreported information and continuously evaluates whether to continue exploring or relay to the base, based on comparing current and predicted future rates of information delivery.
Fig. 3: (a) Robot 1 shares its map with Robot 2, delegating overlapping coverage (blue) and retaining its unique unreported area (green). (b) Robot 1 estimates predicted sensor coverage along its planned path (orange) and compares current vs. predicted rate of information delivery–deciding to continue exploring. (c) After further exploration, the current rate exceeds the predicted rate, triggering relay to the base station.
Fig. 4: Five Test Maps from KTH Indoor Floorplan Dataset [ 28 ] .
Fig. 5: (Left) At T=400 , R1 delegates observed area (blue) to R3. R2, out of range of R3, still learns these areas are delegated via R1. (Right) Each robot compares unique unreported area (green) against predicted future coverage (orange). R1 relays (small predicted coverage); R2 explores; R3, having fully delivered all data, continues exploring.
Fig. 6: Quantitative comparison of PRoID against fixed-schedule baselines in the no-failure scenario, and PRoID-Safe in failure-prone scenarios ( λ∈{1100,900} ). Our methods consistently outperform baselines in total information delivered to the base station.
No Failure Scenario
Failure Scenario ( λ=1100 )
Failure Scenario ( λ=900 )
Method
n=2
n=3
n=4
n=5
n=2
n=3
n=4
n=5
n=2
n=3
n=4
n=5
Periodic Relay ( P=100 )
32.8
41.3
51.5
57.1
24.3
37.4
46.2
48.2
17.7
24.9
44.4
47.1
Periodic Relay ( P=200 )
40.9
51.6
59.0
68.2
30.7
45.8
55.8
56.8
21.9
33.7
53.7
56.9
Periodic Relay ( P=300 )
46.4
56.0
61.8
65.7
35.7
50.9
58.9
59.2
25.6
35.5
56.6
56.7
Final Relay Only
58.4
67.1
68.9
71.4
18.8
49.1
63.0
66.4
16.5
37.2
53.6
61.0
PRoID (Ours)
58.2
68.4
72.3
73.5
34.0
57.4
65.1
68.2
32.3
42.0
58.3
60.1
TABLE I: Coverage ratio (%) at mission end, averaged over all test configurations. Best results per column in bold .
Configuration
Coverage (%)
System Components
PRoID Full System (Ours)
67.9
w/o Relay Handoff
59.8
w/o Traj. & Plan Sharing
53.5
Effect of α — PRoID
α=1.0
49.0
TABLE II: Ablation study. Coverage ratio (%) at n=3 , averaged over test configurations (no-failure scenario).
Fig. 7: (Top) Final Relay Only robot fails at T=560 before returning, losing all data. (Middle) At T=320 , PRoID-Safe triggers relay despite Γnow<αΓpred , as survival probability shifts the criterion ( ΓnowSnow>αΓpredSpred ). (Bottom) Data already relayed; robot continues exploring safely.
Appendix figures & tables2 assets
Supplementary material from the paper’s appendix.
Appendix
parameter
value
Communication Ranged
10m
Raycast Rangel
20m
Frontier penalty distance:
For trajectories ϵtraj
5m
For plans ϵplan
10m
Frontier penalty value γ
106
Appendix
TABLE A.1: Hyperparameters of PRoID and PRoID-Safe
Exploring unknown environments with multi-robot teams can improve efficiency by allowing robots to explore in parallel. However, realizing these gains requires effective information sharing. When communication is intermittent, robots must balance the benefits of sharing information against the cost of diverting from exploration to establish communication. This paper introduces MACE, a decentralized exploration framework that actively evaluates whether establishing communication is worthwhile. At scheduled communication windows, robots estimate the cost of reaching previously identified communication locations. By formulating this decision as a variant of the Vehicle Orienteering Problem, robots evaluate routes based on the travel required to establish communication and the exploration that can be completed along the way. This approach enables robots to communicate more frequently than under purely opportunistic strategies while reducing the unnecessary travel associated with fixed rendezvous strategies. Across a set of simulated environments with varying size and geometry, we demonstrate that MACE reduces the total exploration time by up to 23% compared to existing communication-constrained exploration strategies.
Ben Rossano, Jaein Lim, Jonathan P. How
Aerospace Controls Lab, Massachusetts Institute of Technology, Cambridge, MA, USA · Draper Scholar with the Charles Stark Draper Laboratory, Cambridge, MA · Charles Stark Draper Laboratory, Cambridge, MA, USA
This report presents the OpenSpace Lab's solution to the Competition on Intelligent Information Gathering for Single and Multi-Robot Systems Workshops, organized as part of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) 2026. Our team reached 1st place in the Single-Robot Public Track and 3rd place in both the Single- and Multi-Robot Private Tracks. The single-robot framework utilizes pre-trained map completion predictions for global planning to prioritize unexplored areas. To reconcile map coverage with limited operation time, we introduce a remaining-time-based exploration strategy that integrates homing constraints into the decision-making process. For multi-robot exploration, we utilize a utility-driven target selection strategy that balances observation gains, movement costs, and budget constraints, leveraging shared map and intent data to eliminate redundant search and maximize coordination efficiency. Our solution reached a 61.04% coverage rate in the Single-Robot Public Track, while reaching 39.53% and 39.91% coverage in the Single- and Multi-Robot Private Tracks, respectively. An extended full-length paper based on this report is currently being prepared for submission, and the source code will be released upon acceptance of the full manuscript at https://github.com/OpenSpace-Lab/Indoor-Exploration-IROS2026.
Yuxuan Zhang, Dong Li, Zezhou Sun +5
China University of Mining and Technology-Beijing · Macau University of Science and Technology · Institute of Automation, Chinese Academy of Sciences +3
Teams of unmanned aerial vehicles (UAVs) deployed for search and monitoring missions frequently operate as partially connected networks, forcing each robot to trade off exploring the environment against relaying information to teammates. This tradeoff is especially acute when robots are semantically heterogeneous: an observation that appears uninformative to the robot that made it may be critical to a teammate with complementary detection capabilities. In this work, we formalize this setting as the heterogeneous mission-aware coverage (HMAC) problem, which couples complete multi-robot coverage of an area with capability-constrained mission-relevant target (MRT) discovery under intermittent communication. We then present DORA, a divergence-oriented data-relay algorithm that drives communication by the value of information to the team rather than by discovery alone. DORA quantifies the mission-relevant divergence between a robot's current information state and its estimate of each teammate's knowledge, capturing mission relevance, discovery novelty, sensor uncertainty, and the age of information. We evaluate DORA in simulation across four environments with differing object densities and spatial structure, and validate it on a physical UAV platform. Our results show that DORA improves MRT resolution delay by up to 74.8% over traditional time-based communication scheduling methods.
Jonathan Diller, Fernando Cladera, Camillo Jose Taylor +1
GRASP Laboratory, University of Pennsylvania, Philadelphia, PA 19104, USA