4
Qualcomm believes 6G commercialization will be shaped by sensing, distributed intelligence, and new multi-device experiences that blend the physical and digital worlds
For Qualcomm, the 6G case is about building a network platform that can sense the environment, support distributed AI inference, and model the real world in software. Together, these capabilities begin to define how 6G can support physical AI, a broader vision that connects robots, sensors, networks, and edge computing into collaborative systems.
One of the clearest examples is ISAC (Integrated Sensing and Communications). “ISAC can be used for a variety of applications,” explained Qualcomm engineer Sam Kotler. One of these is drone sensing, where “a base station can send out a reference beam to interrogate the received signals and actually extract information from those signals,” which could include identifying features such as the size of an object or a particular drone. As Kotla says, “It’s very good at tracking activity in the air.”
Qualcomm demonstrated its idea by determining the dimensions of two different drones using a base station with 100 megahertz transmit and receive channels. This setup uses monostatic sensing, where the downlink subpanel transmits a reference signal while the uplink subpanel captures the reflected signal. Background clutter cancellation steps help isolate relevant information. Even more importantly, 6G networks can move data while simultaneously observing and interpreting the physical environment.
The same sensing capabilities feed directly into another 6G use case: the digital twin. Kotla said. RCR Wireless News“The sensing data that we want to collect from all these base stations can be used for a digital twin. It’s just a replica of the real world.” The value of that replica is practical. “What happens is that we’re creating a digital twin of this environment, so any time we want to deploy a resource to the network, we don’t have to actually deploy it first.”Instead, operators can use the model to understand what they want to deploy and what resources they need. “This saves costs and improves network efficiency.”
Qualcomm is also building 6G as an AI inference fabric that can support increasingly complex multimodal and multidevice experiences. As Kotla stated, “6G delivers compute and inference as a service by allowing 6G devices to dynamically offload complex computational tasks to edge servers.” This approach allows devices to access more complex models while conserving local compute and power resources. Rather than forcing all AI workloads onto devices, 6G creates a framework for distributing compute between endpoints and the network edge.
Taken together, ISAC, digital twins, and networks as inference fabrics represent a larger vision of physical AI. Kotla connected those dots through robotics. “Robots are something that is used in both consumer applications and businesses…Robots can be used for a variety of activities and can be used indoors and outdoors…” She said these systems rely on VLA models (Vision, Language, Action Models) running on computing servers that process and fuse data from robots and sensors to generate actions. “But at the same time, we also need compute on AI devices, primarily to run low-latency or mission-critical applications,” Kotla said. “It’s like distributing this computing between the device and the compute model running on the edge server.”
Collectively, 6G provides an opportunity to build a unified network platform that supports the connectivity, sensing, and inference needed to realize the vision of physical AI.
