{"id":"7b410e4e-d47f-43c6-95a3-8fdbc1e9ce72","arxiv_id":"2607.13704","paper_version":1,"verdict":"CONDITIONAL","confidence":"HIGH","novelty_score":5.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":4,"one_line_summary":"A new closed-loop benchmark for planning on distributed-electric-drive trucks, built on nuPlan scenarios with a nonlinear six-wheel truck model and a rollover-risk metric, finds that car-oriented trajectory planners frequently produce rollover-prone plans.","lead":"This paper introduces nuTruck, a simulation benchmark that tests self-driving planners on heavy electric trucks with independently steered and driven wheels, using real driving logs from the nuPlan dataset. It adds a rollover-risk score to the usual safety metrics and reports that car-oriented trajectory planners often produce plans that make such trucks tip over.","discovery_kind":"new_method","skeptic_critique":{"model":"deepseek-v4-flash","headline":"Eq. 12's iLQR-S cost minimizes at nonzero LTR, so the controller-only rollover-prevention results in Tables I/V don't support the central 'falls short' claim as printed.","rationale":"The reader's weakest_assumption (rollover-proxy fidelity) is a real external-validity risk, but the Eq. 12 inconsistency is more load-bearing because it is internal and directly affects the experiment designed to demonstrate the headline negative result. The printed penalty has an interior minimum at nonzero LTR, so the controller optimizes against the NRS metric it is supposed to improve; this is checkable from the text alone and does not require new truck data. The broader benchmark claim has independent support — action planners achieve high NRS without iLQR-S, and plain-iLQR tracking of Plan-R1 already yields NRS ≈ 10 — so the concern weakens but does not destroy the central conclusion. The reader's CONDITIONAL verdict remains appropriate; this concern simply adds a concrete condition. I mark agreement as partial because the reader flagged Eq. 12 in the rationale but selected rollover-proxy fidelity as the weakest assumption.","tokens_in":12189,"tokens_out":8014,"duration_ms":86959,"concrete_test":"Re-run the iLQR-S rows of Tables I and V with a correct one-sided rollover cost, e.g., 0.5 Q_l * max(0, LTR_t - s_safe)^2 (or simply 0.5 Q_l * LTR_t^2 without the (LTR - s_max)^2 term), sweeping Q_l over a plausible range while keeping Q, R, and all other settings fixed; report the chosen Q_l/Q_v. If IDM/PDM/Plan-R1 then reach much higher NRS/CLS-Safe without the observed EPAR drop, the 'controller-only fallback is inadequate' conclusion collapses. If the same qualitative pattern persists, the concern is not decisive and the original claim survives.","verdict_should_be":"UNCHANGED","load_bearing_attack":"Equation (12) defines l' = l + 0.5 Q_l LTR^2 + 0.5 Q_v (LTR - s_max)^2. Since LTR is a nonnegative absolute value (Eq. 8), this quadratic penalty is minimized at LTR* = Q_v s_max/(Q_l+Q_v) > 0; in the limit Q_l -> 0 the target is s_max = 0.9, which is above the NRS safe threshold s_safe = 0.5. The derivative at LTR=0 is -Q_v s_max < 0, so the controller actively pushes LTR away from zero, and the absolute value in Eq. 8 makes the cost non-differentiable at that kink. Thus iLQR-S is not a rollover-prevention controller but a load-transfer-seeking (or, at best, target-relaxed) controller. All Table V and Table I comparisons labeled as 'rollover prevention handled by the controller' are therefore confounded: the NRS gains and the EPAR/CLS losses may be artifacts of this mis-specified cost, not evidence that controller-only rollover prevention cannot balance passability and safety. Since Sec. IV-C's headline conclusion rests on this contrast, the experimental basis for the 'conventional paradigm falls short' claim is compromised. Q_l and Q_v are not reported, so the exact target is unreproducible.","agreement_with_reader":"partial"},"referee_report":{"model":"deepseek-v4-flash","summary":"The paper introduces nuTruck, a closed-loop simulation benchmark for autonomous driving planning on distributed electric-drive trucks (DETs). It builds on nuPlan scenarios, adds a six-wheel nonlinear truck model with independent drive/steer, defines a lateral-load-transfer-based rollover metric (NRS), and evaluates several rule-based and learning-based planners under closed-loop simulation. The central claim is that conventional trajectory planners combined with a tracking controller—even one augmented with rollover prevention—fail to balance kinematic passability and dynamical safety, whereas RL-based action planners trained in the same simulator achieve higher rollover safety. The paper argues that DET planning must incorporate dynamical safety directly.","tokens_in":12399,"tokens_out":6732,"duration_ms":619896,"significance":"If the results hold, nuTruck would be a useful contribution as the first closed-loop, dynamics-aware benchmark specifically for DET planning. The use of real-world nuPlan scenarios, the six-wheel distributed-drive/steer model, and the explicit rollover metric are genuine strengths. The model is validated against TruckSim with low reported errors, and the baseline comparison across rule-based, IL+RL, and action planners is broad. However, a load-bearing flaw in the iLQR-S cost function undermines the paper's headline experimental evidence: as written, the cost drives LTR toward the rollover threshold rather than away from it. Because the conclusion that the conventional planner/controller separation 'falls short' rests on the iLQR-S comparison, the paper needs a substantive correction before the claims can be accepted.","major_comments":[{"comment":"The iLQR-S cost l' = l + 0.5 Q_l LTR^2 + 0.5 Q_v (LTR - s_max)^2 does not reduce rollover risk. Since LTR in Eq. (8) is an absolute value and hence nonnegative, the two LTR-dependent quadratic terms are minimized at LTR* = Q_v s_max/(Q_l + Q_v), which equals s_max = 0.9 when Q_l = 0 and is strictly positive for any finite Q_l. The derivative at LTR = 0 is -Q_v s_max < 0, so the controller actively pushes LTR away from zero toward the rollover threshold. Thus iLQR-S is not a rollover-prevention controller as claimed in Sec. III-D and Sec. IV-C. Consequently, the 'iLQR+S' rows of Table I and the iLQR-S columns of Table V cannot support the conclusion that 'the conventional paradigm, in which the planner ensures collision avoidance and the controller handles rollover prevention, falls short.' Please replace the penalty with a formulation that actually penalizes large LTR (e.g., a hinge/barr","section":"Sec. III-D, Eq. (12)"},{"comment":"The text states that the overall vertical load at each wheel is F_z,i = F_s_z,i + F_d,lon_z,i + F_d,lat_z,i, but Eq. (7) only provides aggregate sums of longitudinal and lateral load transfer over all wheels. No rule is given to distribute these transfers across the three axles or between left and right wheels. Since F_z,i is used in the rolling-resistance model and in the LTR computation, the model is underdetermined and not reproducible as written. Please specify the per-wheel distribution (e.g., based on axle positions, suspension geometry, or the TruckSim configuration).","section":"Sec. III-B-4, Eq. (7)"},{"comment":"The dynamical model is validated only against TruckSim software, and the iLQR controller uses the same model for its rollout as the simulator itself. This perfect-model assumption likely makes the tracking results in Tables I and V optimistic compared to a real deployment where model mismatch exists. The manuscript should qualify the 'high-fidelity' and 'realistic' claims accordingly, and ideally include a robustness experiment with model parameter perturbations or a comparison against a model different from the one used by the controller. This is not fatal to the benchmark concept, but it is important for interpreting the quantitative NRS scores and the transferability of the conclusions to physical DETs.","section":"Sec. IV-B and III-D"}],"minor_comments":[{"comment":"Typos: 'Theotically' should be 'Theoretically'; 'paragraphies' should be 'paragraphs'.","section":"Sec. III-B-1"},{"comment":"Eq. (2) is not fully typeset (e.g., 'Bˆαi'), and the text should clarify that the Pacejka parameters B, C, D, E, S_h, S_v are load-independent; the model does not include normal-load dependence in cornering stiffness, which is a limitation worth stating explicitly.","section":"Sec. III-B-2"},{"comment":"The NRS metric is described only verbally: 'the score decays quadratically from one to zero as a function of the mean LTR over the scenario.' An explicit formula is needed for reproducibility.","section":"Sec. III-E"},{"comment":"Table III has inconsistent spacing (e.g., '1.051e 4 kg' and '6.609e4 kg·m2'). Please use uniform scientific notation.","section":"Sec. III-E / Table III"},{"comment":"Training details for the CaRL planners (number of scenarios, environment steps, reward weights, seeds) are not fully provided; the paper should include enough detail for others to reproduce the RL training in the new benchmark.","section":"Sec. III-C / IV-A"},{"comment":"The convergence curves in Fig. 6 appear to show single-run or aggregate trajectories without error bars. Please report variance across seeds or explain the smoothing procedure.","section":"Fig. 6"}],"recommendation":"major_revision","confidential_remarks":"This is a promising benchmark paper, but the iLQR-S cost in Eq. (12) is a genuine technical error that undermines the headline comparison. The authors should be able to fix it by replacing the penalty with a proper rollover-avoidance cost, reporting the weights, and rerunning the experiments. I would also encourage them to provide code/data access and to more carefully separate 'validated against TruckSim' from 'high-fidelity for real trucks.' The paper is within the journal's scope and, after revision, could make a solid contribution."},"author_rebuttal":null,"desk_editor":null,"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"deepseek-v4-flash","headline":"This paper introduces nuTruck, a benchmark that trains and evaluates autonomous-driving planners on distributed electric-drive trucks (DETs), claiming that the conventional split—planner ensures collision avoidance, controller handles rollo","keywords":["autonomous driving planning","benchmark","distributed electric-drive truck","rollover safety","closed-loop simulation","reinforcement learning planner","load transfer ratio","vehicle dynamics"],"falsifier":"Run a high-fidelity multi-body simulation or a physical test with an instrumented DET executing the same collision-free trajectories used in the paper. Measure actual wheel lift-off, lateral load transfer, or suspension loads and compare rollover events against the LTR threshold. If trajectories with LTR below 0.9 cause wheel lift-off, or LTR above 0.9 does not, the benchmark's safety metric is miscalibrated. Also, re-evaluate the baseline planners using a dynamical model validated against real truck measurements; if a trajectory planner with an advanced controller achieves NRS comparable to t","tokens_in":11904,"feed_emoji":"🚚","tokens_out":4517,"duration_ms":41071,"temperature":0.7,"pith_summary":"The paper claims that for distributed electric-drive trucks, collision-free planning is insufficient: a kinematically feasible trajectory can be dynamically unsafe and cause rollover, and no existing benchmark measures this. It builds nuTruck, a closed-loop simulation that combines real-world driving scenarios with a nonlinear six-wheel, three-axle truck model, and adds a Non-Rollover Score to the standard collision-focused metrics. Experiments show that popular trajectory planners (IDM, PDM, Plan-R1) achieve good collision avoidance but very low rollover safety, while an RL action planner that directly outputs wheel torques and steering angles, trained with hand-designed action patterns, attains markedly higher rollover safety with comparable route progress. If the results hold, DET planning must treat dynamic safety as a planning objective, not a controller afterthought.","feed_headline":"Car planners make electric trucks roll over, new benchmark shows","feed_subtitle":"A closed-loop truck benchmark finds collision-free paths still trigger rollover; action planners do better.","key_machinery":"The load-bearing mechanism is the DET dynamical model integrated into the benchmark: a nonlinear model of a three-axle truck with six independently driven and steered wheels, using a simplified Pacejka tyre formula, rigid-body forces, and dynamic vertical load transfer to compute the LTR, a real-time rollover-risk indicator. The Non-Rollover Score distills LTR traces into a safety metric used in the closed-loop evaluation. The same dynamical model also powers the iLQR tracking controller, so both planning and tracking share the same physics, allowing the benchmark to attribute safety outcomes to the planner rather than to mismatched simulators.","core_discovery":"The central claim is that the standard paradigm for autonomous truck planning—letting the planner ensure kinematic passability and letting the low-level controller handle dynamical safety—breaks down for DETs. On the nuTruck benchmark, trajectory-based planners produce paths that, although collision-free, trigger high lateral load transfer and exceed the rollover threshold, yielding very low Non-Rollover Scores. Adding a rollover penalty to the tracking controller improves those scores but degrades tracking accuracy and route completion. In contrast, an RL planner that predicts low-level control signals directly, and uses action priors that exploit DET kinematic structure (e.g., front-rear o","pith_inferences":["The paper's qualitative conclusion, that trajectory planners risk rollover while action planners are safer, likely transfers to other heavy vehicles, but the precise threshold and relative gains depend on the rollover model's fidelity; a more detailed suspension model might change which planner wins.","A natural next step would be to train an RL planner with an explicit rollover-penalty term in the reward, which the paper does not do; the data suggest this would further narrow the gap between rollover safety and route completion.","The benchmark framework could be adapted to other distributed-drive platforms, such as multi-axle military vehicles or vehicles with higher centers of gravity, making rollover-aware evaluation a standard layer for any high-risk autonomous vehicle.","The action-pattern results imply that the full 12-dimensional control space is unnecessarily hard for learning; a curriculum that starts with low-dimensional priors and progressively releases dimensions could unlock the full DET capability while retaining training stability."],"forward_implications":["Trajectory planners trained or evaluated only on kinematic benchmarks will be judged unsafe on DETs once rollover dynamics are introduced, so future truck planner benchmarks should include a dynamics-based safety metric like NRS.","Hand-designed action priors, such as front-rear opposite steering or Ackermann steering with locked rear wheels, are an effective way to reduce the action space for learning-based truck planners, improving convergence and final route completion.","Reinforcement-learning action planners, even without an explicit rollover penalty, achieve high rollover safety because their smooth actions and comfort-motivated rewards produce less aggressive lateral accelerations than trajectory samplers.","Adding rollover prevention only in the controller is insufficient; it either fails to eliminate rollover or sacrifices tracking accuracy too much to maintain route progress.","The benchmark's metrics, CLS-Safe and NRS, jointly capture collision avoidance and rollover-free progress, offering a template for evaluating planners on other high-risk vehicle types."],"fun_headline_variants":["Safe paths still flip electric trucks in new benchmark","Autonomous truck planners fail rollover test, benchmark shows","New nuTruck benchmark: collision-free doesn't mean rollover-free","Truck planners miss rollover risk, nuTruck benchmark reveals","Benchmark exposes rollover danger from truck planners"],"cache_read_input_tokens":2304,"weakest_assumption_plain":"The empirical conclusions rest on the assumption that the simplified rigid-body rollover proxy—a single LTR with constant center-of-gravity height, no suspension articulation, and a hand-chosen threshold of 0.9—faithfully represents the rollover behavior of a real distributed electric-drive truck; if real trucks roll over under different conditions, the reported safety scores and the relative ranking of planners may not transfer to physical vehicles.","fun_headline_variants_meta":{"raw":{"variants":["Safe paths still flip electric trucks in new benchmark","Autonomous truck planners fail rollover test, benchmark shows","New nuTruck benchmark: collision-free doesn't mean rollover-free","Truck planners miss rollover risk, nuTruck benchmark reveals","Benchmark exposes rollover danger from truck planners"]},"model":"deepseek-v4-flash","effort":"low","cost_usd":0.000148,"raw_usage":{"total_tokens":1027,"prompt_tokens":745,"completion_tokens":282,"prompt_tokens_details":{"cached_tokens":256},"prompt_cache_hit_tokens":256,"prompt_cache_miss_tokens":489,"completion_tokens_details":{"reasoning_tokens":200}},"tokens_in":489,"tokens_out":282,"duration_ms":5663,"temperature":1.0,"reasoning_tokens":200,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-08-02T03:58:50.123373+00:00","model_set":{"reader":"deepseek-v4-flash"},"falsifier":"Run a high-fidelity multi-body simulation or a physical test with an instrumented DET executing the same collision-free trajectories used in the paper. Measure actual wheel lift-off, lateral load transfer, or suspension loads and compare rollover events against the LTR threshold. If trajectories with LTR below 0.9 cause wheel lift-off, or LTR above 0.9 does not, the benchmark's safety metric is miscalibrated. Also, re-evaluate the baseline planners using a dynamical model validated against real truck measurements; if a trajectory planner with an advanced controller achieves NRS comparable to t","supporting_citations":[],"review_version":1}