Postdoc: Safe RL for Spacecraft Autonomy

University of Houston; Houston (TX); On-site; USD 65,000 - 75,000; Full time

Job summary

The University of Houston, based in Sugar Land, TX, seeks a Postdoctoral Researcher for a NASA ECf project on onboard planning for autonomous spacecraft using physics-informed reinforcement learning. The role emphasizes safe, efficient learning-enabled control in uncertain deep-space environments.

The successful candidate will lead efforts in reinforcement learning, safety-critical control, spacecraft dynamics, and real-time hardware-in-the-loop validation, contributing to simulation and

Qualifications

• PhD or terminal degree in a directly related field of specialization related to the work.
• Strong background in reinforcement learning, nonlinear/optimal control, or autonomous systems is highly desirable.
• Experience with embedded hardware-in-the-loop validation is preferred.
• Security-sensitive position requires criminal history check.

Responsibilities

• Receives/reviews progress and evaluates results of experiments or projects under control or supervisory responsibility.
• Recommends changes in research, testing or experimental procedures.
• May be responsible for a single highly technical and complex piece of research equipment.
• May review and evaluate the effectiveness of personnel.
• May plan for and assign personnel to projects under control.
• Operates with latitude for unreviewed action.
• May receive general supervision conferring with higher levels only in unusual situations.
• Performs other job-related duties as required.

Skills

reinforcement learning

nonlinear control

optimal control

control barrier functions

autonomous systems

spacecraft GNC

real-time/embedded implementation

Education

PhD or terminal degree in a directly related field

Job description

The University of Houston, based in Sugar Land, TX, seeks a Postdoctoral Researcher for a NASA ECf project on onboard planning for autonomous spacecraft using physics-informed reinforcement learning. The role emphasizes safe, efficient learning-enabled control in uncertain deep-space environments.

The successful candidate will lead efforts in reinforcement learning, safety-critical control, spacecraft dynamics, and real-time hardware-in-the-loop validation, contributing to simulation and