feat: Robust MPPI (R-MPPI) — 20번째 MPPI 변형#17
Merged
Geonhee-LEE merged 2 commits intomainfrom Mar 18, 2026
Merged
Conversation
Discrete Barrier States MPPI (arXiv:2502.14387) 구현. 밀집 장애물/좁은 통로에서 가중치 퇴화 없이 안전한 궤적 생성. - DBaSMPPIController: log barrier + barrier state dynamics + adaptive σ - DBaSMPPIParams: obstacles, walls, barrier_weight, gamma, exploration_coeff - 28 tests (1295 total), 4-Way 벤치마크 (4 시나리오: dense/dynamic/narrow/noisy) - 문서: MPPI_THEORY §18, TUTORIALS §9.9, README 19종 업데이트 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Tube-MPPI의 분리된 2계층(MPPI→피드백) 대신, 피드백을 MPPI 샘플링 루프 내부에 통합하여 외란 하에서도 추적 가능한 제어를 학습하는 R-MPPI 구현. - RobustMPPIController: 명목+실제 궤적 동시 rollout, 실제 비용 계산 - RobustMPPIParams: disturbance_std, feedback_gain_scale, disturbance_mode 등 - 3 외란 모드: gaussian, adversarial (CVaR-style), none - 28 tests, 4-Way 벤치마크 (Vanilla vs Tube vs Risk-Aware vs Robust, 4 시나리오) - 문서: MPPI_THEORY §19, TUTORIALS §9.10, README/CLAUDE.md 업데이트 Reference: Gandhi et al., RAL 2021, arXiv:2102.09027 Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
RobustMPPIController+RobustMPPIParams(3 외란 모드: gaussian/adversarial/none)Closes #16
Reference: Gandhi et al., RAL 2021, arXiv:2102.09027
Test plan
python -m pytest tests/test_robust_mppi.py -v— 28/28 passedpython -m pytest tests/ -v -q— 1323 passed (기존 무영향)PYTHONPATH=. python examples/comparison/robust_mppi_benchmark.py --all-scenarios— 4 시나리오 정상PYTHONPATH=. python examples/comparison/robust_mppi_benchmark.py --scenario mild_noise— 플롯 생성 확인🤖 Generated with Claude Code