Summary
Distributed intelligent systems often have parts that act on local information but still need to work together to achieve a shared goal. This paper studies how information passed between parts can directly influence their actions and help maintain function even when parts fail or sensors slip. The authors built a four-legged system controlled by fixed policies and showed that using sensor information from peer legs helps the system stay on track better during problems than using only local sensors. They also found that information predicting immediate actions is more useful than information about future states, revealing challenges in measuring useful information for control.
What this means in practice
- •For robotic system developers: Improve multi-limb robot control by sharing sensor data between limbs to maintain performance under failures or sensor errors.
- •For distributed sensor network engineers: Design coordination strategies that use information where it changes receiver actions to enhance system reliability amid partial sensor losses.
Abstract
Distributed intelligence concerns systems in which semi-autonomous components with local dynamics and partial observations coordinate through information exchange to maintain a shared function. This paper proposes an operational way to study such systems: measure information at the interface where a message changes a receiving action, then connect that measure to function by intervention and disturbance evaluation. We instantiate this proposal in DI-Walker, a two-dimensional four-limb embodied plant controlled by frozen Cross-Entropy-Method policies. We compare a controller using each limb's own realized-force sensor with one using the realized-force sensors of peer limbs. Under limb loss, limb slip, and weak central-control dropout, Peer-Sensor has lower late tracking error in several conditions. A corrected finite-history action-predictive estimator shows a substantially larger peer-message gain under compound failure. A future scalar functional-prediction estimator does not show the same stable advantage. We interpret this discrepancy as a methodological result: information useful for an intermediate control action can be hidden by later plant dynamics, redundancy, and context. The paper relates this result to Predictive Information, Transfer Entropy, Directed Information, information-to-go/IT-PAC ideas, empowerment, and the robust control data-rate perspective, while explicitly distinguishing operational predictive gains from exact Directed Information, channel capacity, and a formal data-rate theorem.