- Rating
- 2
- Confidence
- 3
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes RISE, a safety-oriented framework for diffusion-based VLA planning. It combines differentiable road-rule energies with guidance toward a separately trained safety expert, activated by a heuristic risk assessor. The base VLA remains frozen, while the expert is trained using Safe-GRPO. Evaluation on NAVSIM and Bench2Drive reports improvements in planning scores and safety-related metrics.
Critical strengths
- The framework addresses a practical safety-efficiency trade-off. Selectively applying expert guidance is a reasonable way to use a conservative expert without replacing the baseline policy in normal scenarios.
- The reported Bench2Drive improvements are substantial: Driving Score increases from 73.49 to 85.52, and Success Rate from 41.82% to 59.09%. These closed-loop results suggest practical value beyond the smaller average gain on NAVSIM.
Critical weaknesses
- The framework brings established ideas in rule-based energy guidance, backward guidance, constrained policy optimization, and risk gating. While the combination is reasonable, its methodological contribution could be clearer. In particular, the limitations of clean-trajectory guidance are not discussed. The energy gradients at a single denoised estimate generally differ from noisy-distribution guidance, especially at high noise levels. Also the comparisons with standard GRPO or fixed-penalty training would help establish the benefit of Safe-GRPO.
- The results suggest practical value, although the contribution of each design choice remains somewhat unclear. On NAVSIM, the full method achieves 91.5 PDMS versus 91.3 for rule-based guidance alone. Comparisons with ungated combined guidance and direct risk-based expert switching would help explain this gain. The larger Bench2Drive improvements are encouraging, but component ablations would strengthen the evidence, especially given the latency increase from approximately 373 ms to 875 ms.
Questions for authors
- Is backward guidance intended only as heuristic trajectory correction, or is there a distributional interpretation? Please clarify the approximation involved in evaluating energy on the predicted clean trajectory.
- How is the high-risk NAVSIM subset defined, how large is it, and was its selection fixed before hyperparameter tuning? The large gain on this subset is central to the paper’s empirical argument.
- Could you compare Safe-GRPO with standard GRPO or fixed-penalty training under the same settings? It would be helpful to compare against a simpler baseline that directly uses the expert’s trajectory when the same risk threshold is exceeded.
- Could you clarify what RISE adds beyond existing energy-guided planners, such as GuideFlow, and which experimental findings specifically support this advance?
7 comments
Official Response by Authors to Reviewer fZ5h (2/7)
Response 1 - Clean-trajectory guidance and its distributional approximation (W1 and Q1).
W1: The energy gradients at a single denoised estimate generally differ from noisy-distribution guidance, especially at high noise levels.
Q1: Is backward guidance intended only as heuristic trajectory correction, or is there a distributional interpretation? Please clarify the approximation involved in evaluating energy on the predicted clean trajectory.
Backward guidance has a distributional motivation but is implemented as an approximation. The target is energy-reweighted sampling, , whose exact correction averages the energy weight over . RISE instead evaluates the energy at the point estimate , which ignores conditional variance and multimodality, and this error is largest at high noise. Our timing ablation demonstrates that guidance in the first half of denoising alone does not help (90.3 vs. 90.4 PDMS for the baseline), while guidance in the second half alone gives 91.4, close to full RISE (91.5). We will add this approximation and its limitation to the paper.
Detailed responses:
What the point estimate approximates. Under Gaussian noising, a perfectly learned squared-error noise predictor gives . In practice, RISE uses the model's clean-trajectory prediction as a point estimate. The approximation is to evaluate the nonlinear energy weight at this point instead of averaging that weight over the conditional distribution. The guidance calculation therefore omits conditional variance and multimodality, which can matter especially at high noise.
Distributional interpretation and actual update. The distributional motivation is energy-reweighted generation, . Its exact noisy-state score correction is , where
The point-estimate surrogate is , analogous to the point-estimate approximation in diffusion posterior sampling. RISE takes a few gradient steps on and maps to the noise prediction through Eq. (3). This is a distributional motivation; the clean-space update is an approximation, not the exact noisy-state score correction.
Guidance timing. Early-only and late-only guidance use the first and last halves of denoising, respectively. Last-step-only guidance applies the same backward update only at the final denoising step.
Table 1. Guidance timing on the full NAVSIM navtest split. All variants use the same guidance formulation with different active denoising steps.
| Method | NC ↑ | DAC ↑ | TTC ↑ | Comf. ↑ | EP ↑ | PDMS ↑ |
|---|---|---|---|---|---|---|
| ReCogDrive (Baseline) | 97.7 | 97.7 | 94.6 | 100.0 | 86.2 | 90.4 |
| Early-only guidance | 97.7 | 97.6 | 94.5 | 100.0 | 86.1 | 90.3 |
| Last-step-only guidance | 97.7 | 98.7 | 94.6 | 100.0 | 86.8 | 91.1 |
| Late-only guidance | 97.8 | 98.8 | 94.7 | 100.0 | 87.1 | 91.4 |
| RISE | 97.8 | 99.0 | 94.8 | 100.0 | 87.1 | 91.5 |
Last-step-only guidance reaches 91.1 PDMS, compared with 91.4 for late-only, 91.5 for full RISE, and 90.3 for early-only guidance. These results show that high-noise guidance can be unreliable because the point-estimate surrogate omits the conditional variance and multimodality of in , an approximation that matters most at high noise. At low noise, even last-step-only guidance reaches 91.1 PDMS and late-only guidance reaches 91.4 PDMS, close to full RISE at 91.5, so low-noise guidance alone yields a considerable gain and favors late-step guidance in this configuration.
Official Response by Authors to Reviewer fZ5h (3/7)
Response 2 - Component contributions (W2).
W2: Comparisons with ungated combined guidance and direct risk-based expert switching would help explain this gain.
Q3: It would be helpful to compare against a simpler baseline that directly uses the expert’s trajectory when the same risk threshold is exceeded.
The +0.2 PDMS margin of RISE over rule-only guidance on full navtest is small but consistent across three seeds (91.48 ± 0.03 vs. 91.34 ± 0.01), and both requested controls score below both methods: ungated combined guidance reaches 90.9 and direct expert switching 90.6. On Bench2Drive dev10, gated expert guidance raises DS from 74.40 to 79.70 at the same 60% SR, and removing the gate lowers SR to 30%.
Detailed responses:
Always-on mixed guidance on navtest. Table 1. Component ablations on the full NAVSIM navtest split. Parentheses show the PDMS drop in points relative to full RISE (ID 5).
| ID | Rule-Based | Expert-Based | Risk Assessor | NC ↑ | DAC ↑ | TTC ↑ | Comf. ↑ | EP ↑ | PDMS ↑ |
|---|---|---|---|---|---|---|---|---|---|
| 1 | ✗ | ✗ | ✗ | 97.7 | 97.7 | 94.6 | 100.0 | 86.2 | 90.4 (1.1↓) |
| 2 | ✓ | ✗ | ✗ | 97.7 | 98.9 | 94.5 | 100.0 | 87.1 | 91.3 (0.2↓) |
| 3 | ✗ | ✓ | ✗ | 98.0 | 97.9 | 95.1 | 100.0 | 86.0 | 90.7 (0.8↓) |
| 4 | ✓ | ✓ | ✗ | 98.5 | 98.5 | 95.8 | 100.0 | 84.9 | 90.9 (0.6↓) |
| 5 | ✓ | ✓ | ✓ | 97.8 | 99.0 | 94.8 | 100.0 | 87.1 | 91.5 |
Always-on mixed guidance achieves the highest NC (98.5) and TTC (95.8), but at the cost of EP. And it reaches a PDMS of 90.9 versus the full RISE(91.5).
Comparison with simpler alternative on NAVSIM. We compared our method with simpler alternatives that direct expert switching on the full navtest split. It keeps rule guidance enabled and outputs the safety expert’s trajectory when risk exceeds the threshold.
Table 2. Comparison with simpler alternatives on the full NAVSIM navtest split. Parentheses show the PDMS drop in points relative to full RISE.
| Method | NC ↑ | DAC ↑ | TTC ↑ | Comf. ↑ | EP ↑ | PDMS ↑ |
|---|---|---|---|---|---|---|
| ReCogDrive (Baseline) | 97.7 | 97.7 | 94.6 | 100.0 | 86.2 | 90.4 (1.1↓) |
| Direct expert switching | 97.8 | 98.2 | 94.9 | 100.0 | 85.9 | 90.6 (0.9↓) |
| Rule-only | 97.7 | 98.9 | 94.5 | 100.0 | 87.1 | 91.3 (0.2↓) |
| RISE | 97.8 | 99.0 | 94.8 | 100.0 | 87.1 | 91.5 |
Keeping rule guidance active and switching directly to the expert at high risk yields 90.6 PDMS, lower than rule-only guidance(91.3 PDMS), and that directly adopting the expert trajectory is inferior to using it as a soft reference. A direct switch takes the expert trajectory as is. Full RISE uses it as a reference during denoising while continuing to apply road-rule guidance. This gives the planner room to adjust for road compliance and preserve progress. Full RISE reaches 91.5 PDMS, with higher DAC and EP than these simpler alternatives.
W2: The larger Bench2Drive improvements are encouraging, but component ablations would strengthen the evidence
We evaluated the guidance components on the dev10 subsplit on Bench2Drive.
Table 3. Bench2Drive dev10 component ablation. A check mark indicates an enabled component.
| Rule | Expert | Gate | DS ↑ | SR (%) ↑ | Eff ↑ |
|---|---|---|---|---|---|
| ✗ | ✗ | ✗ | 67.00 | 50.00 | 107.00 |
| ✓ | ✗ | ✗ | 74.40 | 60.00 | 111.22 |
| ✗ | ✓ | ✓ | 81.00 | 40.00 | 113.76 |
| ✓ | ✓ | ✗ | 79.20 | 30.00 | 116.90 |
| ✓ | ✓ | ✓ | 79.70 | 60.00 | 124.41 |
Rule-only guidance raises SR from 50% to 60%. Adding gated expert guidance improves DS from 74.40 to 79.70 and efficiency from 111.22 to 124.41 while maintaining SR. Without gating, DS remains similar (79.20), but SR drops to 30%. Gated expert guidance alone achieves the highest DS (81.00), but full RISE achieves higher SR (60% vs. 40%) and efficiency (124.41 vs. 113.76), providing a better balance across these metrics.
Official Response by Authors to Reviewer fZ5h (1/7)
Dear Reviewer fZ5h,
We thank the reviewer for the constructive comments, and for recognizing selective expert guidance as a practical answer to the safety-efficiency trade-off and the closed-loop gains on Bench2Drive. We added guidance-timing, ungated, and direct-switching controls, seed variation, a Bench2Drive component ablation, and an optimized implementation, and will include them in the revised manuscript. In summary:
We hope these results address the reviewer's concerns, and we would be glad to clarify any remaining questions during the discussion period.