Publikation
Constrained Gaussian Process Motion Planning via Stein Variational Newton Inference
Jiayun Li; Kay Pompetzki; An T. Le; Haolei Tong; Jan Peters; Georgia Chalvatzaki
In: Computing Research Repository eprint Journal (CoRR), Vol. abs/2504.04936, Pages 1-14, arXiv, 2025.
Zusammenfassung
Gaussian Process Motion Planning (GPMP) is a
widely used framework for generating smooth trajectories within
a limited compute time–an essential requirement in many robotic
applications. However, traditional GPMP approaches often strug-
gle with enforcing hard nonlinear constraints and rely on
Maximum a Posteriori (MAP) solutions that disregard the full
Bayesian posterior. This limits planning diversity and ultimately
hampers decision-making. Recent efforts to integrate Stein Vari-
ational Gradient Descent (SVGD) into motion planning have
shown promise in handling complex constraints. Nonetheless,
these methods still face persistent challenges, such as difficulties
in strictly enforcing constraints and inefficiencies when the
probabilistic inference problem is poorly conditioned. To address
these issues, we propose a novel constrained Stein Variational
Gaussian Process Motion Planning (cSGPMP) framework, in-
corporating a GPMP prior specifically designed for trajectory
optimization under hard constraints. Our approach improves
the efficiency of particle-based inference while explicitly handling
nonlinear constraints. This advancement significantly broadens
the applicability of GPMP to motion planning scenarios demand-
ing robust Bayesian inference, strict constraint adherence, and
computational efficiency within a limited time. We validate our
method on standard benchmarks, achieving an average success
rate of 98.57% across 350 planning tasks, significantly out-
performing competitive baselines. This demonstrates the ability
of our method to discover and use diverse trajectory modes,
enhancing flexibility and adaptability in complex environments,
and delivering significant improvements over standard baselines
without incurring major computational costs.