Source assessmentCore
Safe Execution of RL Policies via Acceleration-based CBF-QP Constraint Enforcement for Real-World Robotic Deployments
Safe robotic reinforcement learningAcademic
Assessment outcome
total 5/6 (actionability 2 + authority 1 + currency 2)
Total5/6
Actionability2/2
Authority1/2
Currency2/2
Authorship & scope
Attribution (G4 evidence)
No evidence recorded for this source.
Issuer authority (evidence)
No evidence recorded for this source.
Issuers, who it governs, legal force and content are on the full record.
Eligibility gates
G1 · Retrievablepass
Passed in screening.
G2 · AI nexuspass
Passed in screening.
G3 · Governance nexuspass
Passed in screening.
G4 · Attributablepass
Passed in screening.
G5 · In forcepass
Passed in screening.
Scored criteria
Actionability
2/2No rationale recorded.
At each control step, the QP computes the generalized accelerations ¨q⋆ ∈R n that satisfy all constraints while minimizing a quadratic cost written as a weighted sum of task errors
Authority
1/2No rationale recorded.
All authors are with the CNRS–AIST Joint Robotics Laboratory (JRL), IRL3218, AIST, Tsukuba, Japan
Currency
2/2No rationale recorded.
Classification
Coverage topicSafe robotic reinforcement learning
PerspectiveAcademic
Lifecycle stage5 Deploy
Layermodel
GranularityNot recorded