Teleoperated driving — where a remote human drives a vehicle through transmitted sensor data — demands both low latency and high data quality. Compressing the sensor stream reduces bandwidth but degrades the remote driver's situational awareness. Scheduling radio resources reduces latency but has limited allocation.
The authors (arXiv:2603.23387) train two integrated RL agents: one optimizing compression (balancing transmission efficiency against data quality) and one optimizing scheduling (allocating radio resources by priority). The key result: the joint system outperforms either agent alone, especially under network congestion.
The improvement isn't just additive. In congested conditions, the compression agent can preemptively reduce quality before the scheduler runs out of resources, and the scheduler can prioritize critical frames that the compression agent has marked as important. The two agents develop a complementary strategy that neither discovers independently.
The through-claim: joint optimization of compression and scheduling outperforms serial optimization because the two decisions are coupled through network state. Deciding how much to compress without knowing the radio schedule is suboptimal; scheduling without knowing the compression level wastes resources. The joint system exploits the coupling, trading quality in non-critical frames for latency in critical ones.