Abstract
Ants show an incredible ability to collectively transport complex irregular-shaped objects with seemingly simple coordination. Achieving similarly effective collective transport with robots has potential applications in many settings, from agriculture to construction to disaster relief. In this paper we investigate a simple decentralized strategy for collective transport in which each agent acts independently without explicit coordination. Using a physics-based model, we prove that this strategy is guaranteed to successfully transport a complex object to a target location, even though each agent only knows the target direction and does not know the object shape, weight, its own position, or the position and number of other agents. Using two robot hardware platforms, and a wide variety of complex objects, we validate the strategy through extensive experiments. Finally, we present a set of experiments to demonstrate the versatility of the simple strategy, including transport by 100 robots, transport of an actively moving object, adaptation to change in goal location, and dealing with partially observable goals.
Original language | English (US) |
---|---|
Pages | 47-54 |
Number of pages | 8 |
State | Published - 2013 |
Externally published | Yes |
Event | 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013 - Saint Paul, MN, United States Duration: May 6 2013 → May 10 2013 |
Conference
Conference | 12th International Conference on Autonomous Agents and Multiagent Systems 2013, AAMAS 2013 |
---|---|
Country/Territory | United States |
City | Saint Paul, MN |
Period | 5/6/13 → 5/10/13 |
All Science Journal Classification (ASJC) codes
- Artificial Intelligence
Keywords
- Collective Intelligence
- Multi-Robot Systems
- Transport