ManiDreams: An Open-Source Library for Robust Object Manipulation via Uncertainty-aware Task-specific Intuitive Physics
This work addresses the challenge of uncertainty in real-world robotic manipulation, providing a practical tool for researchers and practitioners, though it is incremental as it builds on existing intuitive physics models.
The authors tackled the problem of robust robotic manipulation under uncertainty by developing ManiDreams, a modular framework that integrates uncertainty representation and constraint-based planning, which maintained robust performance on ManiSkill tasks where baseline methods degraded significantly.
Dynamics models, whether simulators or learned world models, have long been central to robotic manipulation, but most focus on minimizing prediction error rather than confronting a more fundamental challenge: real-world manipulation is inherently uncertain. We argue that robust manipulation under uncertainty is fundamentally an integration problem: uncertainties must be represented, propagated, and constrained within the planning loop, not merely suppressed during training. We present and open-source ManiDreams, a modular framework for uncertainty-aware manipulation planning over intuitive physics models. It realizes this integration through composable abstractions for distributional state representation, backend-agnostic dynamics prediction, and declarative constraint specification for action optimization. The framework explicitly addresses three sources of uncertainty: perceptual, parametric, and structural. It wraps any base policy with a sample-predict-constrain loop that evaluates candidate actions against distributional outcomes, adding robustness without retraining. Experiments on ManiSkill tasks show that ManiDreams maintains robust performance under various perturbations where the RL baseline degrades significantly. Runnable examples on pushing, picking, catching, and real-world deployment demonstrate flexibility across different policies, optimizers, physics backends, and executors. The framework is publicly available at https://github.com/Rice-RobotPI-Lab/ManiDreams