LIBERO
A simulation benchmark designed to evaluate the generalization capability of robot manipulation policies. It includes subsets such as LIBERO-Spatial, which tests generalization across spatial position variations, and LIBERO-Plus, which covers multiple task types and object combinations.
Timeline (last 90 days)
CARE certification validated on LIBERO provides statistical guarantees only for episodes from the same distribution as LIBERO and does not automatically transfer to open-world settings or larger-scale models.
LIBERO is a commonly used imitation learning benchmark in the robot manipulation field, including spatial, object, goal, and long suites; its limitation is that the task distribution is relatively fixed and scenario diversity is lower than in real deployment environments.
CARE is currently validated only on four LIBERO suites and two agents (Qwen3.5-9B and Llama-3.1-8B).
On a single LIBERO robot planning task, one episode costs $0.035 for Glimpse and $0.249 for GPT-6 Astra.
LIBERO-PeRM builds a procedural data generation pipeline on top of the LIBERO environment, ultimately constructing five task suites containing 312 tasks, with high-quality demonstrations, rich metadata, and preference satisfaction metrics.
LIBERO stands for Lifelong Robot Learning Benchmark, a widely used robot manipulation benchmark platform that provides multiple tabletop manipulation environments, standardized task definitions, and demonstration data formats.
The LIBERO benchmark contains four task suites: Spatial, Object, Goal, and Long; LIBERO-Pro is its enhanced version, increasing task complexity and the number of steps
LIBERO-RIG is a VLA model benchmark test whose design perturbs only the robot hardware and setup, keeping the LIBERO tasks themselves completely unchanged.
LIBERO-RIG covers 11 perturbation dimensions, with 5 severity levels set for each dimension, combining into 210 test conditions across four LIBERO suites.
The LIBERO series is a widely used manipulation benchmark in the robot learning field, containing a large number of language-conditioned long-horizon manipulation tasks, used to evaluate the generalization and continual learning ability of policies.
4 more timeline events
All Facts (14)
CARE certification validated on LIBERO provides statistical guarantees only for episodes from the same distribution as LIBERO and does not automatically transfer to open-world settings or larger-scale models.
50%UnverifiedLIBERO is a commonly used imitation learning benchmark in the robot manipulation field, including spatial, object, goal, and long suites; its limitation is that the task distribution is relatively fixed and scenario diversity is lower than in real deployment environments.
50%UnverifiedCARE is currently validated only on four LIBERO suites and two agents (Qwen3.5-9B and Llama-3.1-8B).
50%UnverifiedOn a single LIBERO robot planning task, one episode costs $0.035 for Glimpse and $0.249 for GPT-6 Astra.
50%UnverifiedLIBERO-PeRM builds a procedural data generation pipeline on top of the LIBERO environment, ultimately constructing five task suites containing 312 tasks, with high-quality demonstrations, rich metadata, and preference satisfaction metrics.
50%UnverifiedLIBERO stands for Lifelong Robot Learning Benchmark, a widely used robot manipulation benchmark platform that provides multiple tabletop manipulation environments, standardized task definitions, and demonstration data formats.
50%UnverifiedThe LIBERO benchmark contains four task suites: Spatial, Object, Goal, and Long; LIBERO-Pro is its enhanced version, increasing task complexity and the number of steps
50%UnverifiedLIBERO-RIG is a VLA model benchmark test whose design perturbs only the robot hardware and setup, keeping the LIBERO tasks themselves completely unchanged.
50%UnverifiedLIBERO-RIG covers 11 perturbation dimensions, with 5 severity levels set for each dimension, combining into 210 test conditions across four LIBERO suites.
50%UnverifiedThe LIBERO series is a widely used manipulation benchmark in the robot learning field, containing a large number of language-conditioned long-horizon manipulation tasks, used to evaluate the generalization and continual learning ability of policies.
50%UnverifiedIn simulation environments, RoboRSI achieves the highest success rates on benchmarks such as LIBERO, LIBERO-PRO, LIBERO-Plus, and RoboTwin, exceeding the strongest baseline by 2.7 to 11.0 percentage points.
50%UnverifiedThe community is advancing standardized simulation benchmarks such as LIBERO, SimplerEnv, and HumanoidBench, as well as the DROID dataset based on real robots.
50%UnverifiedLIBERO simulation successfully runs long-horizon tasks on Mac for the first time, with GR00T achieving a 100% success rate, WAM achieving 98%, and a 2.8-billion-parameter VLA small model achieving 96%.
50%UnverifiedThe paper validates on three platforms: the simulation benchmarks RoboTwin and LIBERO, as well as a real robot platform.
50%