We report the first time-synchronized protocol stack running on a crystal-free device. We use an early prototype of the Single-Chip micro Mote, SCµM, a single-chip 2×3 mm 2 mote-on-a-chip, which features an ARM Cortex-M0 micro-controller and an IEEE802.15.4 radio. This prototype consists of an FPGA version of the micro-controller, connected to the SCµM chip which implements the radio front-end. We port OpenWSN, a reference implementation of a synchronized protocol stack, onto SCµM. The challenge is that SCµM has only on-chip oscillators, with no absolute time reference such as a crystal. We use two calibration steps - receiving packets via the on-chip optical receiver and RF transceiver - to initially calibrate the oscillators on SCµM so that it can send frames to an off-the-shelf IEEE802.15.4 radio. We then use a digital trimming compensation algorithm based on tick skipping to turn a 567 ppm apparent drift into a 10 ppm drift. This allows us to run a full-featured standards-compliant 6TiSCH network between one SCµM and one OpenMote. This is a step towards realizing the smart dust vision of ultra-small and cheap ubiquitous wireless devices.

TerraSwarm applications, or swarmlets, are characterized by their ability to dynamically recruit resources such as sensors, communication networks, computation, and information from the cloud; to aggregate and use that information to make or aid decisions; and then to dynamically recruit actuation resources. The TerraSwarm vision cannot be achieved by a single vendor providing the components as an integrated system. What is needed instead is the swarm equivalent of the common, general framework that has recently enabled smartphones and similar devices to rapidly deploy and serve a vast range of often unanticipated applications by recruiting resources and composing services. The SwarmOS must support continual reconfiguration of applications and of its own service definitions without ever having the luxury of a clean restart. It must also support richly heterogeneous computing. TerraSwarm protocols will need to detect compromises, distinguish trusted from untrusted data and resources, and be robust to the presence of a certain number of malicious nodes.