REVIEW 20 cited by
Riemannian Motion Policies
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
We introduce the Riemannian Motion Policy (RMP), a new mathematical object for modular motion generation. An RMP is a second-order dynamical system (acceleration field or motion policy) coupled with a corresponding Riemannian metric. The motion policy maps positions and velocities to accelerations, while the metric captures the directions in the space important to the policy. We show that RMPs provide a straightforward and convenient method for combining multiple motion policies and transforming such policies from one space (such as the task space) to another (such as the configuration space) in geometrically consistent ways. The operators we derive for these combinations and transformations are provably optimal, have linearity properties making them agnostic to the order of application, and are strongly analogous to the covariant transformations of natural gradients popular in the machine learning literature. The RMP framework enables the fusion of motion policies from different motion generation paradigms, such as dynamical systems, dynamic movement primitives (DMPs), optimal control, operational space control, nonlinear reactive controllers, motion optimization, and model predictive control (MPC), thus unifying these disparate techniques from the literature. RMPs are easy to implement and manipulate, facilitate controller design, simplify handling of joint limits, and clarify a number of open questions regarding the proper fusion of motion generation methods (such as incorporating local reactive policies into long-horizon optimizers). We demonstrate the effectiveness of RMPs on both simulation and real robots, including their ability to naturally and efficiently solve complicated collision avoidance problems previously handled by more complex planners.
Forward citations
Cited by 20 Pith papers
-
Space Is Intelligence: Neural Semigroup Superposition for Riemannian Metric Generation
A single Encoder-Router network uses semigroup superposition of frame, modulation, and coefficient parameters to produce a scene-specific Riemannian metric field that supports zero-shot geodesic planning after trainin...
-
Geometry-Aware Sampling-Based Motion Planning on Riemannian Manifolds
A sampling-based planner approximates Riemannian geodesic distances via midpoints with third-order accuracy and uses retractions plus natural gradients for local planning, producing lower-cost trajectories than Euclid...
-
SAIL: Faster-than-Demonstration Execution of Imitation Learning Policies
A full-stack speed-adaptation system lets imitation-learned robot policies execute up to 3-4x faster than human demonstrations while preserving task success rates.
-
ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation
ReKep encodes robotic tasks as optimizable Python functions over 3D keypoints that are generated automatically from language and RGB-D input, enabling real-time hierarchical planning on single- and dual-arm platforms ...
-
TempoVLA: Learning Speed-Controllable Vision-Language-Action Policies
TempoVLA learns a single VLA policy with controllable execution speed via variable-speed trajectory augmentation and explicit speed conditioning.
-
World-Task Factorization for Robot Learning
Introduces world-task factorization for robot policies using Bayesian evidence and AICON graph plus learned modulator, outperforming baselines with zero-shot generalization in heterogeneous robotics settings.
-
Safe and Steerable Geometric Motion Policies for Robotic Dexterous Manipulation
SafePBDS uses pullback control barrier functions and a task manifold action interface to generate certifiably safe, steerable motions on high-DOF robots from objectives defined on arbitrary geometric spaces.
-
cuRoboV2: Dynamics-Aware Motion Generation with Depth-Fused Distance Fields for High-DoF Robots
cuRoboV2 unifies B-spline optimization, GPU-native dense signed distance fields, and scalable whole-body kinematics and dynamics to achieve 99.7% success on payloaded manipulators and 99.6% collision-free IK on 48-DoF...
-
Deep Reactive Policy: Learning Reactive Manipulator Motion Planning for Dynamic Environments
DRP couples a transformer policy pretrained on 10M cuRobo trajectories and refined by student-teacher finetuning with a point-cloud reactive goal proposer (DCP-RMP) to outperform prior planners in dynamic manipulation.
-
Physics-informed Neural Time Fields for Prehensile Object Manipulation
POM-NeTF extends physics-informed neural time fields from robot motion planning to prehensile object manipulation, enabling fast, demonstration-free planning with re-grasping in cluttered environments.
-
EL-AGHF: Extended Lagrangian Affine Geometric Heat Flow
EL-AGHF evolves a trajectory and a dual multiplier together through a PDE, enforcing dynamic admissibility in inadmissible control directions with finite penalties.
-
DexWild: Dexterous Human Interactions for In-the-Wild Robot Policies
DexWild co-trains dexterous robot policies on in-the-wild human hand interactions recorded with a low-cost system and limited robot data, achieving 68.5% success in unseen environments and 5.8x better cross-embodiment...
-
OptiWorld: Optimal Control for Video World Generation under Physical Constraints
OptiWorld inserts a classical optimal-control layer that extracts a world state, plans an optimal trajectory on a geometric manifold under physical constraints, and renders the video conditioned on that trajectory.
-
Riding the Shifting Potential: When Reactive Control Suffices for Multi-Goal Behavior
Nullspace projections on a graph-based model enable reactive control to achieve 100% success in non-convex planar pushing across 100 configurations, versus 0% for steepest descent and ~55% for diffusion policy, withou...
-
Multimodal Human-Intent Modeling for Contextual Robot-to-Human Handovers of Arbitrary Objects
A gaze-plus-language pipeline enables a robot to select tabletop objects from a remote user's monitor and generate human-aware grasps for handover, with real-world tests on YCB objects.
-
Building Forest Inventories with Autonomous Legged Robots -- System, Lessons, and Challenges Ahead
The paper reports 16 autonomous forest-inventory missions with an ANYmal quadruped in three countries, with mission autonomy above 80% of distance traveled and a 2 cm typical DBH accuracy figure inherited from the aut...
-
RoboTwin: A Robotic Teleoperation Framework Using Digital Twins
A dual digital twin framework for remote robotic surgery reduces operator workload and network bandwidth compared with conventional video feedback.
-
General Covariant Action Modeling: Constructing Generalized Manifolds via Spatio-Temporal Decoupling
GAM framework uses arc-length parameterization for temporal invariance and schema-affine factorization for geometric invariance to build a covariant action manifold integrated into VLA models for improved generalizati...
-
Task-Oriented Edge-Assisted Cross-System Design for Real-Time Human-Robot Interaction in Industrial Metaverse
A predicted-motion digital twin framework with a human-in-the-loop meta-learning algorithm lowers teleoperation drawing error from 0.0712 m to 0.0101 m.
-
Learning Dynamics under Environmental Constraints via Measurement-Induced Bundle Structures
Measurement-aware control barrier functions are re-framed through a fiber bundle geometry for Neural ODE dynamics learning, but the claimed convergence and safety guarantees rely on an oracle update and a faulty union bound.
Discussion (0). Continue with ORCID to comment.