Tapia LabUniversity of New Mexico
Menu
Tapia Lab robotics, biology, and gaming identity over a New Mexico mountain landscape Albuquerque, New Mexico
Adaptive Motion Planning Research Group

Planning and learning for complex systems.

We develop adaptive methods for robots, human–AI teams, and molecular systems—turning uncertainty into intelligent motion.

Explore our research Meet the lab
01 Robot learning
02 Human–AI teaming
03 Safe autonomy
04 Computational biology
What connects our work

Intelligence in motion.

Across every project, we ask how complex systems can move, decide, and adapt more effectively—especially when information is incomplete.

01

Motion planning & robot learning

Learning-enhanced methods for navigation, manipulation, interception, and decision making in dynamic environments.

 02

Human–AI teaming

How people adapt to autonomous systems—and how autonomy can adapt in return over long periods of collaboration.

 03

Safe & adaptive autonomy

Robust decision making under uncertainty, equipment failure, adversarial conditions, and changing operating environments.

 04

Computational biology

Motion-planning and geometric models for molecular interactions, protein motion, cellular signaling, and assembly.
Featured research
01 / 04 · Motion planning & robot learning

Machine learning was improving our planning methods long before the current AI wave.

Our WAFR 2004 work used machine learning to make the first motion planner auto-adaptive —an early anchor for the lab’s continuing work at the intersection of learning and planning.

Explore this research area

Learning where planning needs attention

A learned model helps direct computational effort toward difficult, informative regions of the problem.

WAFR 2004historical contribution
Learningguides motion
Movementthrough complex spaces

From the lab

Research in motion available for download.

View ALL Publications
New publication

Using LiDAR symmetries to improve value estimation

At decision time, the method imagines the robot encountering the same surroundings from several rotationally equivalent orientations. It evaluates what the learned policy would do in each case, selects the most promising action, and transforms that action back to the robot’s actual orientation—improving value estimation without additional training.

View publication
Our team

The people behind the work.

The Tapia Lab brings together students and collaborators working across robotics, artificial intelligence, human–AI interaction, and computational biology.

Lydia E. Tapia, Professor of Computer Science and Tapia Lab Director
Lab director

Lydia E. Tapia, PhD

Professor of Computer Science · Tapia Lab Director

Across the lab’s projects, Professor Tapia studies how planning and learning algorithms can exploit structure revealed through interaction to operate effectively in high-dimensional, dynamic, and incompletely modeled systems.

Full profile CV Contact
View all lab members
01

Students & postdocs

Graduate students, undergraduate researchers, and postdoctoral scholars contribute to projects across the lab’s research areas.

02

Alumni

Lab alumni continue into faculty, research, industry, and doctoral positions, carrying their experience into new institutions and new problems.

Outreach & impact

Research should travel.

See what we offer
01

Research pathways

We help students encounter research through hands-on projects and sustained mentoring, from a first lab experience through advanced study.

02

Learning in the community

Lab members translate robotics, computing, and AI ideas into approachable demonstrations, workshops, and conversations.

03

Broadening participation

We work to make computing and robotics more welcoming by creating visible, supported pathways into the field.

Work with us

Curious about intelligent motion? Let’s build what comes next.

Join or collaborate