A Purdue University team led by Indian American researcher Somali Chaterji has developed a 3D detection system that may prove a game changer for companies manufacturing autonomous vehicles, industrial robotics, delivery robots and drones.
The innovative patent-pending AGILE3D, a cutting-edge 3D object detection system, outperforms 3D lidar perception pipelines during resource contention, according to a media release from the West Lafayette, Indiana-based research institution.
“AGILE3D is the first adaptive, contention- and content-aware 3D object detection system tailored for embedded GPUs, or graphics processing units,” said Chaterji an associate professor of agricultural and biological engineering in Purdue’s College of Agriculture and College of Engineering.
“The system can dynamically adjust detection strategies based on real-time hardware constraints and varying input data,” added Chaterji who also holds a courtesy appointment in the Elmore Family School of Electrical and Computer Engineering.
Baseline methods introduced at the Conference on Neural Information Processing Systems (NeurIPS), the European Conference on Computer Systems (EuroSys) and the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) provide reference points showing that across datasets and platforms, AGILE3D meets stringent latency objectives while delivering up to +3% accuracy over adaptive controllers and up to +7% over widely used static 3D detectors.
Read: Waabi raises $1 billion, partners with Uber to deploy self-driving cars
Chaterji said AGILE3D is broadly applicable wherever a robot or vehicle needs fast 3D perception on a tight onboard computer budget. She said the strongest fit is autonomous driving, where lidar frames must be processed in real time and perception is critical to safety.
“Beyond cars, AGILE3D can benefit delivery robots and drones, industrial/mobile robotics, augmented reality/virtual reality perception, and outdoor autonomy in digital agriculture and forestry, especially when the platform relies on an embedded GPU and must keep latency predictable for smoother, safer operation,” she said. “That matters most when multiple onboard workloads run at once, such as perception, tracking and planning, alongside in-cabin infotainment or driver-monitoring features that can also draw on GPU resources.”
Research about AGILE3D was published at ACM MobiSys 2025, the International Conference on Mobile Systems, Applications and Services.
Chaterji disclosed AGILE3D to the Purdue Innovates Office of Technology Commercialization, which has applied for a patent from the U.S. Patent and Trademark Office to protect the intellectual property.
Chaterji said resource contention occurs when multiple workloads share the same embedded GPU and memory system at the same time. An example is a ride-hailing robotaxi where camera perception, lidar processing, tracking, mapping and planning run together on the same embedded GPU.
One of 3D lidar’s key constraints is its update rate, or how often the sensor delivers a new point cloud frame, which is a fresh 3D snapshot of surroundings, she said.
Read: Waymo autonomous vehicle strikes child in California; safety review underway
Chaterji said AGILE3D maintains performance under resource contention through two coordinated layers: its multibranch execution framework (MEF) and its contention- and content-aware reinforcement learning (CARL) controller.
During comprehensive evaluations, AGILE3D achieved state-of-the-art performance, maintaining high accuracy across varying hardware contention levels and latency budgets of 100 to 500 milliseconds.
Chaterji continues to develop the technology to enable dense scene understanding on onboard computers, where 3D semantic segmentation must run reliably under tight compute and memory budgets.
Chaterji and her team received funding to develop AGILE3D through her National Science Foundation CAREER grant and a National Science Foundation grant for their CHORUS center.
Chaterji got her PhD in Biomedical Engineering from Purdue University, winning the Chorafas International Award (2010), College of Engineering Best Dissertation Award (2010), and the Future Faculty Fellowship Award (2009). She did her Post-doctoral Fellowship at the University of Texas at Austin in the Department of Biomedical Engineering
Chaterji is also a lab-to-bedside commercialization enthusiast and is a scientific advisor to the IC2 Institute at the University of Texas at Austin since 2014. She won Purdue’s Seed-for-Success Award in 2016 for winning a research grant of more than $1 million.