LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
hub
curobo: Parallelized collision-free minimum-jerk robot motion generation
16 Pith papers cite this work. Polarity classification is still indexing.
16
Pith papers citing it
abstract
This paper explores the problem of collision-free motion generation for manipulators by formulating it as a global motion optimization problem. We develop a parallel optimization technique to solve this problem and demonstrate its effectiveness on massively parallel GPUs. We show that combining simple optimization techniques with many parallel seeds leads to solving difficult motion generation problems within 50ms on average, 60x faster than state-of-the-art (SOTA) trajectory optimization methods. We achieve SOTA performance by combining L-BFGS step direction estimation with a novel parallel noisy line search scheme and a particle-based optimization solver. To further aid trajectory optimization, we develop a parallel geometric planner that plans within 20ms and also introduce a collision-free IK solver that can solve over 7000 queries/s. We package our contributions into a state of the art GPU accelerated motion generation library, cuRobo and release it to enrich the robotics community. Additional details are available at https://curobo.org
hub tools
citation-role summary
background 1
citation-polarity summary
roles
background 1polarities
background 1representative citing papers
BiDexGrasp supplies a 9.7-million-grasp bimanual dexterous dataset built via two-stage synthesis and a coordinated geometry-size-adaptive model that generates grasps for unseen objects.
GraspIT provides ~316k annotated RGBD frames with ~2.3M slip-test-validated 6-DoF grasp candidates and a bidirectional sim-to-real registration pipeline, all released as open-source Docker containers.
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
Optimization-guided diffusion replaces sampling perturbations with constrained corrections to enforce physical feasibility in generative robot policies at inference time.
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
Video2Sim2Real turns a single human video into a deployable robot manipulation skill by reconstructing a digital twin, anchoring motions to object-centric simulator configurations, and bridging sim-to-real gaps with imitation learning and residual RL.
AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.
A trajectory optimization method performs geometry-aware updates in function space via natural functional gradients and Monte-Carlo estimation on a smoothed surrogate objective to improve feasibility and smoothness in robotic manipulation.
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
SynManDex generates human-like dexterous grasps for robots from synthetic human pre-grasps via retargeting and force-closure optimization, reporting 86.4% stability, 4.67/5 human-likeness, 80.7% sim success, and 83.3% real-robot success.
GD2P generates and learns dexterous hand poses for nonprehensile pushing and pulling by combining contact-guided sampling, physics-based filtering, and a geometry-conditioned diffusion model, demonstrated on Allegro and LEAP hands in real-world tests.
MimicIK applies conditional flow matching with an FK consistency loss and MIP backbone to learn IK from 8848 teleoperation demos on a 6-DOF robot, reporting 4.65 mm mean position error, 92.01% 10 mm success rate, 7.99% spike rate, and 6.74 ms latency while remaining stable near singularities.
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.
citing papers explorer
-
LIBERO-Safety: A Comprehensive Benchmark for Physical and Semantic Safety in Vision-Language-Action Models
LIBERO-Safety supplies a scalable benchmark, data-generation pipeline, and 19,664-demonstration dataset that exposes a generalization-safety tension in current VLA models where diverse training improves collision avoidance but task success stays limited by trajectory quality and semantic understandi
-
BiDexGrasp: Coordinated Bimanual Dexterous Grasps across Object Geometries and Sizes
BiDexGrasp supplies a 9.7-million-grasp bimanual dexterous dataset built via two-stage synthesis and a coordinated geometry-size-adaptive model that generates grasps for unseen objects.
-
GraspIT: A Dataset Bridging the Sim-to-Real gap and back for Validated Grasping SE(3) Pose Generation
GraspIT provides ~316k annotated RGBD frames with ~2.3M slip-test-validated 6-DoF grasp candidates and a bidirectional sim-to-real registration pipeline, all released as open-source Docker containers.
-
E-TTS: A New Embodied Test-Time Scaling Framework for Robotic Manipulation
E-TTS introduces a plug-and-play test-time scaling method for embodied tasks that unifies reasoning-action sampling with history buffers and closed-loop refinement to improve performance on manipulation benchmarks.
-
Grounding Generative Policies in Physics: Optimization-Guided Diffusion for Robot Control
Optimization-guided diffusion replaces sampling perturbations with constrained corrections to enforce physical feasibility in generative robot policies at inference time.
-
AnnotateAnything: Automatic Annotation of 3D Assets for Robot Manipulation
AnnotateAnything converts passive 3D assets into manipulation-ready assets by combining vision-language reasoning for semantics with parallel physics pipelines for executable action annotations such as grasps and articulations.
-
Video2Sim2Real: Full-Stack Autonomous Dexterous Skill Acquisition from a Single Human Video
Video2Sim2Real turns a single human video into a deployable robot manipulation skill by reconstructing a digital twin, anchoring motions to object-centric simulator configurations, and bridging sim-to-real gaps with imitation learning and residual RL.
-
AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding
AffordanceVLA proposes a VLA model with affordance-aware modules (Which2Act, Where2Act, How2Act) in a Mixture-of-Transformer trained in three stages to improve robotic manipulation.
-
Natural Functional Gradients for Smooth Trajectory Optimization
A trajectory optimization method performs geometry-aware updates in function space via natural functional gradients and Monte-Carlo estimation on a smoothed surrogate objective to improve feasibility and smoothness in robotic manipulation.
-
MagicSim: A Unified Infrastructure for Executable Embodied Interaction
MagicSim is a unified embodied interaction infrastructure built on a deterministic batched runtime and shared MDP that supports diverse world construction, execution, task evaluation, automatic rollout generation, and interactive agent interfaces.
-
SynManDex: Synthesizing Human-like Dexterous Grasps from Synthetic Human Pre-Grasps
SynManDex generates human-like dexterous grasps for robots from synthetic human pre-grasps via retargeting and force-closure optimization, reporting 86.4% stability, 4.67/5 human-likeness, 80.7% sim success, and 83.3% real-robot success.
-
Learning Geometry-Aware Nonprehensile Pushing and Pulling with Dexterous Hands
GD2P generates and learns dexterous hand poses for nonprehensile pushing and pulling by combining contact-guided sampling, physics-based filtering, and a geometry-conditioned diffusion model, demonstrated on Allegro and LEAP hands in real-world tests.
-
MimicIK: Real-Time Generative Inverse Kinematics from Teleoperation with FK Consistency
MimicIK applies conditional flow matching with an FK consistency loss and MIP backbone to learn IK from 8848 teleoperation demos on a 6-DOF robot, reporting 4.65 mm mean position error, 92.01% 10 mm success rate, 7.99% spike rate, and 6.74 ms latency while remaining stable near singularities.
-
World Simulation with Video Foundation Models for Physical AI
Cosmos-Predict2.5 unifies text-to-world, image-to-world, and video-to-world generation in one model trained on 200M clips with RL post-training, delivering improved quality and control for physical AI.
- Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot
- MorphIt: Flexible Spherical Approximation of Robot Morphology for Representation-driven Adaptation