Online Replanning in Belief Space for Partially Observable Task and Motion Problems
A toolbox for trajectory optimization of dynamical systems
Synthesizing safe robot policies in joint physical-belief spaces with deep RL! - CoRL 2023
A standardized method to give AI agents a persistent philosophical and ethical operating context.
Robust dexterous grasping with variational neural beliefs (IROS 2026)
Learned regression heuristics for A* search over belief states — and an evaluation of when they help (and when they don't).
The robot navigates a discrete grid while interacting with an uncertain crowd characterized by distance, flow direction, and density, which are only partially observable. Social navigation behaviors—such as following crowd flow, yielding, overtaking, waiting, or searching for gaps—are explicitly modeled as actions.
Deterministic OSINT engine with belief-space reasoning -- 50+ platform recon, Bayesian confidence scoring, significance analysis, and automated intelligence briefs. TypeScript + Express + React.
Robot self-localization in a partially observable, non-deterministic environment — solved with A* over belief states (optimal) and local beam search (fast), plus adversarial worst-case start-state search.
Experiments in dynamic treatment regimes using reinforcement learning.
Bayesian belief-state tracking of a sensorless roomba using a probabilistic proximity detector and decision-theoretic action selection — extends belief-space localization with recursive filtering and a mobile, utility-driven LocatorBot.
To associate your repository with the belief-space topic, visit your repo's landing page and select "manage topics."