Skip to content
Home / Catalog / RNEA Inverse Dynamics with Hidden Payload Identification

RNEA Inverse Dynamics with Hidden Payload Identification

  • Task ID: robotics.rnea_inverse_dynamics_dh
  • Domain: robotics
  • Subdomain: inverse_dynamics
  • Status: final
  • Benchmark set: seed42 (60 tasks)
  • Tags: inverse_dynamics, newton_euler, dh_parameters, manipulator, rnea, spatial_vector, payload_identification, system_identification

Runtime and requirements

  • Estimated time: 60-120 minutes
  • Python: >=3.9
  • Packages: numpy>=1.24.0
  • GPU required: no
  • Network required: no

Public input and output contract

Inputs

  • task_info.json (data): Robot specification: kinematic and inertial parameter arrays (a, alpha, d, theta_offset; per-link mass, com, inertia_diag), gravity_base vector, static_pose_index.
  • trajectory.npz (data): Precomputed joint trajectory samples: q, qd, qdd arrays of shape [N_samples, n_dof].
  • calibration.npz (data): Calibration motion set with joint torques measured on the physical robot: arrays q, qd, qdd, tau.

Outputs

  • analysis.py (code): Agent implementation of inverse dynamics; reads data/ and writes tau_history.npy and verification metrics.
  • tau_history.npy (data): Computed joint torques for each trajectory sample.
  • verification_data_1.npy (data): Scalar forward-dynamics verification metric (max acceleration residual).

Public repository files

View this task in ASI-Bench

Formal benchmark task directories in the public repository are metadata-only. Versioned prompts and inputs are distributed through the pinned benchmark dataset.

Provenance

This task is included in the current seed42 benchmark set at dataset revision f11a199f71fb4b854ac43a1bf548d5df519141a9.

This page is generated only from files tracked in the public ASI-Bench repository at commit f18382f03faf. Submission bundles, run logs, private scoring configuration, and private reference answers are not read by this page generator.