Teams of robots working on a shared task. The main questions are what they need to share (positions, maps, plans, beliefs) and what happens when sharing fails: dropped links, delays, or a robot that is wrong or lying. This is the main topic of my PhD.
Concepts
- Resilient consensus: agreeing on a value when some members lie, with an interactive explainer.
- Byzantine fault tolerance: robots that behave arbitrarily, and telling faults from attacks.
- Collaborative SLAM: several robots building one map, and what crosses the link.
- Semantic coordination: coordinating on descriptions, between robots with different sensors.
- 3D scene graphs, filed under semantic mapping.
- Aerial swarms and Singapore scenarios, filed under field robotics.
- Safe control, runtime monitoring and failure recovery for teams.
- Human-robot trust: which robot should an operator believe when two disagree?
Comparisons
Entities
Groups and platforms that come up here: MIT SPARK Lab, MARVL Lab, Kimera-Multi, the Crazyflie and Crazyswarm. The entity index has the rest.
The thesis threads that grow out of this are robust robotics, multi-robot multimodal perception and long-term autonomy.
Open questions
- Which cyber-physical security methods (independent monitors, invariants, attack detection) work for a team that moves?
- What is a simple, useful definition of “this robot is behaving oddly”?
- How does a team tell a broken teammate from a lying one, with a witness the suspect can’t control?
- Robot teams move, so the communication graph changes as they coordinate. Which robustness guarantees survive that?
Papers
| Paper | Year | Venue | Domain | Threads |
|---|---|---|---|---|
| Discovering antagonists | 2026 | Robotics and Autonomous Systems 2026 | land | robustness |
| Hickory | 2026 | arXiv preprint | land | perception, long-term |
| Equivariant graph CBF | 2025 | arXiv 2025 | air | robustness |
| DRACo-SLAM2 | 2025 | arXiv preprint | sea | perception, robustness |
| DeNeR pursuit-evasion | 2025 | IEEE MRS 2025 | air | robustness |
| Energy-constrained coverage | 2025 | arXiv 2025 | general | robustness, long-term |
| Intermittent faults in swarms | 2025 | arXiv 2025 | general | robustness |
| AAPD model | 2025 | Royal Society Open Science 2025 | land | robustness, long-term |
| Confidence-weighted trust consensus | 2025 | arXiv 2025 | land | robustness |
| CURB-SG | 2024 | ICRA 2024 | land | perception, long-term |
| Hydra-Multi | 2023 | IROS 2023 | land | perception, robustness |
| Role-based MADDPG pursuit | 2023 | ICRA 2023 | air | robustness |
| Blockchain token economy | 2023 | Science Robotics 2023 | land | robustness |
| Decentralized Blocklist Protocol | 2023 | AAMAS 2023 | general | robustness |
| Resilient task allocation | 2021 | IEEE Robotics and Automation Letters 2021 | land, air | robustness |
| Blockchain vs W-MSR | 2020 | Frontiers in Robotics and AI 2020 | land | robustness |
| Formal methods for robots survey | 2019 | ACM Computing Surveys 52(5) | general | robustness |
| Multi-robot assembly survey | 2018 | ACM Computing Surveys 2018 | land | robustness |
| Crazyflie 2.0 platform | 2017 | MMAR 2017 | air | robustness |
| Crazyswarm | 2017 | ICRA 2017 | air | robustness |
| MCMAS | 2017 | International Journal on Software Tools for Technology Transfer 19(1) | general | robustness |
| Spoof-resilient networks | 2017 | Autonomous Robots 2017 (conference version at RSS 2015) | air, land | robustness |
| Safety barrier certificates | 2016 | ACC 2016 | land | robustness |
| PRISM swarm verification | 2010 | ANTS 2010, Swarm Intelligence (LNCS 6234) | general | robustness |
| Vicsek model convergence | 2003 | IEEE Transactions on Automatic Control, vol. 48, no. 6, 2003 | general | robustness |
| Paper | Year | Venue | Domain | Threads |
|---|---|---|---|---|
| AGT-CV | 2026 | ECCV 2026 Workshops (CDEL) | air, land | perception |
| Above and Below | 2026 | arXiv preprint | sea | perception |
| AUSLUN | 2026 | arXiv preprint | sea, air | perception |
| HEROIC | 2026 | arXiv preprint | air, land | perception |
| Reputation-based consensus | 2026 | arXiv preprint | general | robustness |
| SGM-SLAM | 2026 | arXiv preprint | land | perception |
| FRAC-MARL | 2026 | arXiv preprint | general | robustness |
| CERPE | 2026 | arXiv preprint | land | perception |
| Conformal map fusion | 2026 | arXiv preprint | general | robustness, perception |
| PERSEPHONE perception | 2026 | ICARCV 2026 | land | perception |
| CILC | 2026 | arXiv preprint | general | perception, robustness |
| Trust-aware rollout | 2026 | arXiv preprint | land | robustness |
| SABER | 2026 | arXiv preprint | land | robustness, perception |
| Multi-agent prompt injection | 2026 | arXiv preprint | general | robustness |
| RigidShift | 2026 | arXiv preprint | air | robustness |
| Multi-robot language-grounded planning | 2025 | arXiv preprint | land | perception |
| ROMAN | 2024 | RSS 2025 | land, air | perception, robustness |
| MDBC | 2021 | ICLR 2021 | land, air | robustness |
| PCM | 2018 | ICRA 2018 | land | robustness, perception |
Crazyflie 2.0 Quadrotor as a Platform for Research and Education in Robotics and Control Engineering
Towards Spatial Perception for Heterogeneous Robot Collaboration in Subterranean Mining Environments
Byzantine Resilience at Swarm Scale: A Decentralized Blocklist Protocol from Inter-robot Accusations
Other subfields: perception, mapping and localisation, semantic mapping, planning and navigation, control, robot learning, safety and verification, security, Human-robot interaction, field robotics.