ABB and Salzburg patent AI to cut robot energy

ABB and Salzburg researchers patent AI to cut energy in industrial robots. The move marks a formal step to turn research into practical gains for energy efficiency in automation, anchored by the Josef Ressel Center for Intelligent and Secure Industrial Automation, known as JRZ ISIA.

The partnership pairs Salzburg University of Applied Sciences with ABB’s Machine Automation Division B and R to apply artificial intelligence to drive systems. The goal is straightforward: use AI to optimize how industrial robots consume power during operation, without compromising performance or reliability. Deployment data shows the project is designed to migrate ideas from the lab into real world drive systems, a path that many AI for industry initiatives struggle to navigate. The case study reports that translating advanced research into practical solutions for industrial drive hardware is the core ambition.

The initiative centers on energy efficiency within industrial automation, a pressing lever for plants facing rising energy costs and sustainability targets. The AI system is intended to assess and adjust how motors, drives, and controllers behave across typical motion cycles. Rather than replacing control logic, the approach seeks to augment it with data-driven optimization that respects safety constraints and deterministic performance. In practice this means the AI would monitor energy use in real time and steer control decisions to reduce wasted power, recover energy where feasible, and smooth transitions between motion phases. ABB and Salzburg emphasize that the work is not about flashy tech for its own sake but about meaningful energy reductions baked into existing control architectures.

From a plant management perspective, the integration story matters as much as the concept. The collaboration highlights that the AI system is being designed to fit into current industrial drive ecosystems, which implies data interfaces, edge processing, and secure communication with control software. The integration requirements are nontrivial: reliable data from sensors, robust state estimation for real time decisions, and safeguards that guarantee energy optimization never disrupts cycle timing or product quality. For asset owners, the practical questions are about cycle times and throughput. The project aims to preserve or improve cycle integrity while reducing energy per cycle, with throughput serving as a key metric to verify that energy savings do not come at the expense of production capacity.

The work also has a clear implications for labor. When automation moves from concept to deployment, skilled trades support becomes essential for integration, commissioning, and ongoing maintenance. Automation engineers and system integrators will need to align AI-driven energy decisions with existing safety interlocks and machine-vision or inspection workflows. In this setting, automation does not supplant craft labor; it augments it by reducing idle energy, guiding maintenance focus on actuator efficiency, and enabling smarter fault detection. Electricians, technicians, and inspectors will increasingly work alongside AI-enabled controls to sustain energy performance over time.

Industry observers will want to watch how quickly the AI drive system can adapt to different robot types and production lines, and how durable the energy gains prove under faulted or dynamic operating conditions. The emphasis on translating research into practical drive-system solutions suggests a measured pathway: proof of energy savings in controlled pilots, followed by scaled deployment with clear ROI tied to reduced energy bills and potential life-cycle benefits for motors and drives. If ABB and Salzburg can demonstrate consistent energy reductions without sacrificing throughput, the project could set a meaningful benchmark for AI in industrial drives.