Our collaborative project, “NIFA: Collaborative Research: ARMOR-Harvest: Aerial Robotic Morphing for Occlusion Resilient Apple Harvesting,” has received support from NSF. This project will enable a team of aerial and ground robots to actively move leaves and branches, reveal hidden fruit, and improve robotic harvesting in dense and unstructured orchard environments.

• Collaborators: Dr. Zhaojian Li at Michigan State University and Dr. Vasileios Tzoumas at the University of Michigan.
• Collaborative award page 1
• Collaborative award page 2
• Collaborative award page 3

Congratulations to Sibo, Davood, and Harsh on receiving Texas A&M Graduate and Professional School Research and Presentation Travel Awards.

Dr. Minghui Zheng will serve as a co-principal investigator on the six-year, $24.9 million NSF Autonomous Robotic Metallurgist Materials Innovation Platform (ARM-MIP) at Texas A&M University. The CtrlRobot Lab will contribute robotic solutions that integrate automation and artificial intelligence to accelerate the design, synthesis, and testing of new metal alloys.

• NSF award page
• NSF news release
• Texas A&M Engineering news

Congratulations to Sibo, Davood, and Jiuzhou on receiving IEEE RAS Travel Support to attend and present at IROS 2026, helping cover the cost of sharing their work with the robotics community.

Congratulations to Jiurun, recipient of a Fall 2026 Continuing Student Fellowship; Dharmik, recipient of a Fall 2026 Research Advancement Fellowship; and Chang, recipient of a Summer 2026 Graduate Summer Research Grant — three well-deserved recognitions of their research progress and continued promise in the lab.

We are excited to share that several recent papers from our group will be presented at major robotics, machine learning, and computer vision conferences in 2026. These works span foundation-model safety for robotics, contact-aware manipulation, motion planning, human-robot motion prediction, transformable aerial robots, and egocentric world models.

• Modular Safety Guardrails Are Necessary for Foundation-Model-Enabled Robots in the Real World; ICML 2026.
• Learning When to See and When to Feel: Adaptive Vision-Torque Fusion for Contact-Aware Manipulation; IROS 2026.
• GAIDE: Graph-based Attention Masking for Spatial- and Embodiment-aware Motion Planning; IROS 2026.
• Real-Time 3D Motion Prediction for Human-Robot Collaboration via Bayesian-Optimized Diffusion Models; IROS 2026, T-ASE Transfer.
• MorphoCopter: Design, Modeling, and Control of a New Transformable Quad–Bi Copter; IROS 2026, T-Mech Transfer.
• Egocentric World Model for Photorealistic Hand-Object Interaction Synthesis; ECCV 2026.

Two recent papers from our group were presented at the Manufacturing Science and Engineering Conference 2026. These works focus on intelligent robotic disassembly for end-of-life electronics, including vision-language-action models for selective desktop disassembly and vision-model benchmarking for irregular component segmentation in e-waste.

• Vision-Language-Action Models for Selective Robotic Disassembly: A Case Study on Critical Component Extraction from Desktops.
• Evaluating Large and Lightweight Vision Models for Irregular Component Segmentation in E-Waste Disassembly; Journal of Manufacturing Science and Engineering Transfer.

Our group presented several works at the 2026 American Control Conference, covering intelligent automation for electronics remanufacturing, adaptive human-robot collaboration, and learning-enhanced motion planning.

• Redefining End-of-Life: Intelligent Automation for Electronics Remanufacturing Systems; ACC 2026 Tutorial.
• Adaptive Motion Planning via Contact-Based Intent Inference for Human-Robot Collaboration; ACC 2026.
• Warm-Starting Optimization-Based Motion Planning for Robotic Manipulators via Point Cloud-Conditioned Flow Matching; ACC 2026.

“Toward Generalist Neural Motion Planners for Robotic Manipulators: Challenges and Opportunities” — this survey systematically reviews deep learning approaches for robotic manipulator motion planning and maps modern neural architectures to core planning primitives such as sampling, steering, collision checking, and trajectory optimization. We analyze current limitations — including data scarcity, generalization, safety, and real-time deployment — and outline a roadmap toward scalable and generalist neural motion planners. Check out the paper, project page, and paper list for more details.

In this work, we present the design, control, and experimental validation of our novel morphing quadrotor, capable of reducing its width by up to 70% to navigate extremely narrow passages. The innovative mechanical architecture and control framework ensure stable and controllable flight across all morphed configurations. Check out the paper for more details.

“Real-Time 3D Motion Prediction for Human-Robot Collaboration via Bayesian-Optimized Diffusion Models” — we propose a two-stage distillation strategy that compresses a pretrained diffusion-based human motion prediction model into a lightweight MLP-based one-step diffusion model, enabling robots to reliably anticipate possible human motions in real time, even faster than the human motion data streaming frequency. Check out the paper for more details.

“RAISE: A Robot-Assisted Selective Disassembly and Sorting System for End-of-Life Phones” — we propose an automated system for the disassembly and sorting of end-of-life phones, achieving high efficiency and accuracy. The system is designed to be cost-effective and highly scalable, transforming a previously unprofitable recycling process into a sustainable and profitable solution. Check the link for details.

We were excited to participate in the recent MEEN Open House, welcoming faculty, families, alumni, and future students to explore our ongoing research. Visitors experienced demonstrations of our foldable drones and robotic systems for human-robot collaborative disassembly, and had the opportunity to operate the robotic arm directly and complete object-grasping exercises themselves.

We were excited to share that our research group participated in the IEEE International Conference on Robotics and Automation (ICRA) 2025, held in Atlanta, Georgia. During the event, our team presented three papers showcasing our recent advancements in robotic motion planning and manipulation.

“SIMPNet: Spatial-Informed Motion Planning Network” — supplementary materials are available via this link. Check SIMPNet’s GitHub repository and project website for more information.

Our paper “Integrating Uncertainty-Aware Human Motion Prediction Into Graph-Based Manipulator Motion Planning” has been selected for the Best Student Paper Award of the DSCD Robotics Technical Committee for 2024. The paper proposes a human-aware motion planning framework for HRC to effectively compute collision-free motions for manipulators when conducting collaborative tasks with humans. Check the paper for details: IEEE Xplore.

Our research has been honored with the Best Student Paper Award from the Technical Committee on Vibrations of ASME’s Dynamic Systems & Control Division. The paper, “Robust Iterative Learning for Collaborative Road Profile Estimation and Active Suspension Control in Connected Vehicles,” was presented at the 2024 Modeling, Estimation and Control Conference and introduces a novel framework for collaborative road profile estimation using iterative learning control and disturbance observation techniques. For more details, visit our publication on arXiv.

“Bayesian-Optimized One-Step Diffusion Model with Knowledge Distillation for Real-Time 3D Human Motion Prediction” — we drastically improved inference speed compared to the state-of-the-art diffusion-based motion predictor, and are the first to achieve real-time 3D human motion prediction without noticeable degradation in performance. Check the project page for more information.

“Improving Disturbance Estimation and Suppression via Learning among Systems with Mismatched Dynamics” — supplementary materials are available via this link.

Demo and code for our IEEE RA-L paper “TransFusion: A Practical and Effective Transformer-based Diffusion Model for 3D Human Motion Prediction” are now released. Check the project page for more information.

In an interview posted by the College of Engineering, Dr. Zheng discusses her academic background and research — her journey into mechanical engineering, her motivations for joining the department, and the aims of her research. Read the full interview.

Welcome to the J. Mike Walker ’66 Department of Mechanical Engineering, Dr. Zheng! Dr. Minghui Zheng’s primary area is control and robotics, including task sequence and robotic motion planning in human-robot collaborative environments, with a focus on improving the disassembly, recycling, and remanufacturing of end-of-use products such as e-waste. Read the full article.