Aptiv PULSE equips Carter Gen 3 robot

Robust.AI announced this week that its Gen 3 Carter collaborative mobile robot will rely on Aptiv PLC’s PULSE intelligent perception system, a move the company says sharpens navigation in busy, real world warehouses. Carter is designed to augment existing warehouse operations, handling order-fulfillment picking, point-to-point transport, and mobile sorting without the need for new infrastructure, an appealing promise for facilities chasing speed without sprawling capital projects. The PULSE sensor, Aptiv notes, blends radar and vision to deliver safer, more reliable decision making in environments that routinely throw glare, dust, moisture changes, and obstructions at perception systems. In practice, that means Carter can operate among people and equipment with fewer misreads caused by reflective surfaces or clutter, a common stumbling block for vision-only systems.

Deployment data shows a path toward scalable, safety-conscious automation in warehousing. The case study reports that integrating the PULSE-enabled perception stack with Robust.AI’s software-defined automation is intended to support a broader market of physical AI that can adapt to real world variability. The emphasis is not on a one-off demo but on a steady, repeatable capability that can scale across multiple facilities while maintaining safety standards demanded by modern fulfillment operations. Jay Bellissimo of Aptiv, who leads the intelligent systems group, framed the collaboration as a practical step toward functional safety in real environments, underscoring that perception must work reliably not just under ideal conditions but in the noise of an active warehouse floor.

From a practitioner standpoint, the juxtaposition is clear. The Carter Gen 3 platform is designed to operate alongside human workers and existing materials handling processes, not to displace them. The core value proposition centers on improving cycle times and throughput by reducing the time workers spend fetching and moving items, while maintaining high accuracy in routing and sortation tasks. Yet the numbers behind those gains are by design discreet in early releases. The case study notes that cycle times and throughput metrics have not been publicly disclosed, but the intent is to deliver measurable improvements in velocity without requiring expensive new infrastructure. In practice, that creates a calculable ROI path: faster task completion, lower labor friction on busy shifts, and more flexible staffing as automation handles repetitive transport and sorting while humans focus on tasks that still benefit from dexterity and judgment.

Two key constraints and tradeoffs surface in any warehouse automation rollout like this. First, integration requirements are nontrivial. Perception by itself is not enough; it must fuse with the robot’s planning stack, the facility’s warehouse management system, and safety controls. The case study stresses a safety-first approach, implying that facilities will need to validate functional safety pathways, calibration routines, and ongoing software updates to preserve performance across changing conditions. Second, the workforce implication is nuanced. Carter is intended to augment craft labor, not merely replace it; technicians and system integrators will play a crucial role in tuning sensors, validating routes, and maintaining the software stack as conditions shift with seasonal demand or layout changes. This is where deployment data shows the practical payoff but also where expectations must be managed: gains depend on disciplined integration, operator training, and a clear governance model for updating perception and planning parameters.

Looking ahead, the combination of Aptiv PULSE and Robust.AI’s software-defined automation could push more warehouses toward scalable, safety-focused automation with fewer upfront infrastructure costs. Yet observers should watch for how quickly cycle times translate into sustained throughput gains across multiple facilities, how integration footprints evolve with different WMS ecosystems, and how shipment profiles, including dense, irregular, or high-aisle layouts, test the vendor claims. The case study’s rhetoric about safety-critical perception spanning dynamic conditions is encouraging, but the practical demo will be in ongoing pilots, real-world deployments, and the ability to keep performance stable as environments evolve.