- Rating
- 2
- Confidence
- 1
- Informativeness
- 2
- Presentation
- 2
- Soundness
- 2
Read review
Paper summary
The paper proposes CIB, which constrains cross-entity communication through predicted physical states to reduce contextual shortcut reliance in end-to-end driving. Experiments report planning improvements across multiple interaction structures and driving benchmarks, with controlled analyses examining sensitivity to appearance and physical changes.
Critical strengths
- The paper introduces an explicit physical-state interface for cross-entity interaction. Controlled comparisons show consistent planning improvements across different interaction structures and evaluation settings.
Critical weaknesses
- The evidence that CIB addresses harmful shortcut reliance remains indirect. Appearance decodability and trajectory sensitivity do not establish that contextual cues cause planning errors.
- Evidence for CIB’s additional value on stronger recent models remains limited. It is unclear whether the benefits of physical constraints or additional supervision observed on weaker baselines persist in models with stronger prediction and interaction representations. Although modest improvements are reported on SparseDriveV2, repeated runs or confidence intervals are not provided for these gains, making it difficult to distinguish them from training and evaluation variability. Controlled comparisons and shortcut analyses on strong baselines are also limited, leaving uncertainty about whether the observed improvements stem from the proposed communication constraint.
Questions for authors
- What evidence connects the baseline’s appearance sensitivity to actual planning errors, and shows that CIB reduces these errors by limiting harmful shortcut reliance?
- Could you evaluate CIB across multiple strong recent planners under matched conditions, examining both planning performance and responses to appearance and physical interventions? Please provide repeated-run results or confidence intervals to assess whether the improvements are reliable across these models.
6 comments
Post 2 of 5: Q1. Testing communication content with raw-feature controls
We added a raw branch to the complete CIB model while retaining its physical predictions, supervision, and interaction modules. A matched physical branch adds capacity while keeping source communication in the physical representation. The comparison tests the consequence of restoring raw-feature access, beyond the physical inductive bias and auxiliary loss shared by these variants.
The following point-estimate diagnostics report clean DS/SR on Bench2Drive; training-seed variability is not reported for these ablations. Auxiliary denotes adding physical supervision to the original host. They are distinct from the repeated main comparisons in our third reply.
| Host | Physical auxiliary | Full CIB | CIB + raw | CIB + physical |
|---|---|---|---|---|
| VADv2 | 75.4/50.5 | 76.1/51.4 | 76.0/51.4 | 76.2/51.8 |
| DriveTransformer-L | 62.3/36.8 | 63.3/38.2 | 63.4/37.7 | 63.5/38.6 |
| HiP-AD | 86.3/69.1 | 86.6/69.5 | 86.8/69.5 | 86.7/70.0 |
| AlignDrive | 88.4/71.8 | 88.4/72.3 | 88.7/72.3 | 88.5/72.7 |
| SparseDriveV2 | 89.2/70.5 | 89.6/71.4 | 89.5/71.4 | 89.6/71.8 |
Clean scores alone give a limited separation between the full and raw-branch variants. We therefore use the appearance-induced collision-error increment from the preceding reply and calculate direct differences of increments. A negative value favors the physically mediated comparator.
| Host | Physical branch minus raw, 95% CI | Full CIB minus raw, 95% CI |
|---|---|---|
| VADv2 | -1.2 [-3.8, 1.4] | -1.0 [-3.6, 1.6] |
| DriveTransformer-L | -1.1 [-4.1, 1.8] | -0.9 [-3.9, 2.0] |
| HiP-AD | -0.9 [-2.7, 1.2] | -0.7 [-2.6, 1.4] |
| AlignDrive | -0.5 [-2.4, 1.6] | -0.3 [-2.2, 1.8] |
| SparseDriveV2 | -0.8 [-2.8, 1.2] | -0.5 [-2.5, 1.5] |
VeteranAD+'s corresponding native corruption-loss contrast is -0.6 [-1.6, 0.5] for the physical branch minus raw, and -0.5 [-1.5, 0.7] for Full CIB minus raw. These are PDMS-loss differences, not collision-rate differences.
The point-estimate pattern is informative: adding a physical branch preserves the smaller error increment, while adding a raw branch moves the response toward the original host. Because every direct interval includes zero, this is directional evidence for the communication-content hypothesis; it does not statistically isolate the incremental contribution of the restriction.
We accordingly sharpened the paper's contribution to a physically grounded communication interface with local structural guarantees. The name is now Constrained Interaction Bottleneck. On replaced edges, source-dependent messages use predicted physical states and mode probabilities. The network's retained target, temporal, and other pathways remain part of the planner. The controlled experiments evaluate this architectural hypothesis within their stated scope.
Manuscript locations: Table 27 on p. 42; Table 28 on p. 43; Table 30 on p. 45; Table 31 on p. 46; Table 32 on p. 47; Table 33 on p. 48; Table 34 on p. 49; Table 35 on p. 50; Table 36 on p. 51; Table 37 on p. 52; Table 38 on p. 53; Table 39 on p. 53; Section 3.2 on p. 4, Section 4.3 on p. 7.
Post 3 of 5: Q2. Multiple strong planners and uncertainty across training runs
We expanded the study to VADv2, DriveTransformer-Large, HiP-AD, AlignDrive, SparseDriveV2, and VeteranAD+. This includes planner families beyond the SparseDrive hosts used in the original controlled study. HiP-AD is treated as layerwise trajectory refinement; VeteranAD+ is evaluated in its native NAVSIM-v1 setting. We keep these settings explicit rather than treating every refinement mechanism as temporal autoregression.
For each main host-versus-CIB comparison, we report three training seeds, 1, 42, and 123. Within-seed CIB-minus-host differences determine the paired Student-t 95% interval with two degrees of freedom. The full tables include individual runs and mean plus sample standard deviation.
| Host | Mean DS, host to CIB | DS difference, 95% CI | Mean SR, host to CIB | SR difference, 95% CI |
|---|---|---|---|---|
| VADv2 | 74.433 to 75.600 | 1.167 [-4.058, 6.391] | 49.533 to 51.400 | 1.867 [-4.965, 8.698] |
| DriveTransformer-L | 61.367 to 63.067 | 1.700 [-4.014, 7.414] | 35.767 to 38.200 | 2.433 [-7.768, 12.634] |
| HiP-AD | 85.667 to 86.167 | 0.500 [-3.498, 4.498] | 68.033 to 69.400 | 1.367 [-4.349, 7.082] |
| AlignDrive | 87.933 to 87.833 | -0.100 [-4.098, 3.898] | 70.933 to 71.833 | 0.900 [-2.578, 4.378] |
| SparseDriveV2 | 88.700 to 89.333 | 0.633 [-2.351, 3.618] | 69.367 to 71.400 | 2.033 [-1.952, 6.018] |
VeteranAD+'s mean PDMS is 90.900 for the host and 91.133 with CIB; the paired increment is 0.233 [-0.771, 1.237]. SR differences are percentage points.
The repeated results expose both transfer and variability. Mean SR improves on all five Bench2Drive hosts, while AlignDrive's mean DS is nearly unchanged. Every paired interval crosses zero, so the current three-seed evidence does not resolve a reliable gain for each strong model. The revised claim is that CIB transfers across independent implementations and exhibits host-dependent benefits, with uncertainty stated explicitly.
The original controlled topologies were also repeated. Their reported three-seed means are:
| SparseDrive variant | L2, host to CIB | PDMS, host to CIB | DS, host to CIB | SR, host to CIB |
|---|---|---|---|---|
| Sequential | 0.612 to 0.563 | 81.7 to 85.1 | 43.7 to 46.5 | 17.4 to 19.4 |
| Parallel | 0.581 to 0.547 | 82.9 to 86.3 | 45.0 to 48.1 | 18.7 to 21.2 |
| Iterative | 0.621 to 0.565 | 83.6 to 87.7 | 47.2 to 50.3 | 20.4 to 22.0 |
These favorable aggregate directions complement the strong-host estimates. Together with the direct branch controls, they make clear where the design has been implemented, what was compared, and how much the available measurements establish.
Manuscript locations: Table 30 on p. 45, Table 32 on p. 47, Table 34 on p. 49, Table 36 on p. 51, Table 27 on p. 42, Table 38 on p. 53, Table 1 on p. 7; Section 4.5 on p. 8.
Post 1 of 5: Q1. Connecting appearance sensitivity to planning errors
Thank you for distinguishing trajectory sensitivity from harmful planning behavior. We added collision-error measurements under matched appearance conditions, with progress reported alongside them. This directly evaluates whether a changed visual condition accompanies additional errors, beyond changing the predicted trajectory.
The table shows reference-to-changed collision rates in percent and the within-model error increment in percentage points. The reported intervals are 95% confidence intervals. Each comparison uses the same host and evaluation conditions.
For VADv2, DriveTransformer-L, and HiP-AD, the host's appearance-induced error increment has an interval above zero. This supplies a direct behavioral connection for the tested conditions. Full CIB has smaller point estimates of both changed-condition collision error and the appearance-induced increment on all five hosts.
We checked progress because a planner can reduce collision exposure by making less progress. Under changed appearance, progress increases from 89.7 to 91.9 for VADv2, 85.8 to 88.8 for DriveTransformer-L, 94.0 to 95.2 for HiP-AD, 95.4 to 96.0 for AlignDrive, and 95.4 to 96.3 for SparseDriveV2. These paired patterns make uniformly more conservative behavior an incomplete explanation of the collision-error results.
VeteranAD+ supplies a separate native NAVSIM-v1 diagnostic. RGB corruption reduces the host's PDMS from 90.9 to 88.7, a loss of 2.2 with interval [0.6, 4.2]. CIB changes from 91.1 to 89.5, a loss of 1.6 with interval [0.1, 3.3]. We report this as a native corruption test, separately from the CARLA collision analysis.
The revised empirical claim is specific: the tested appearance changes affect planning errors, and physically mediated models show favorable error and progress point estimates under those changes. To isolate the role of communication content, we additionally compare raw-feature and physical branches directly, as described in our next reply.
Manuscript locations: Table 31 on p. 46, Table 33 on p. 48, Table 35 on p. 50, Table 37 on p. 52, Table 28 on p. 43, Table 39 on p. 53; Section 4.4 on p. 8.