Pith.

Robotics · arXiv:2611.10498 v1 · submitted 7 Nov 2026 · 54 references

EmbodiedIntentBench: Benchmarking Intent-Driven Runtime Adaptation for Mobile Robotic Missions

Rajat Bhattacharjya, Changwoon Lee, Hyeonjong Ju, Sing-Yao Wu, Hamidreza Alikhani, Zhuoyi Yang, Ian Harris, Nalini Venkatasubramanian

show 1 more author

Nikil Dutt

The paper says

“Mobile robotic sensing systems must adapt to operator requirements, limited resources, changing connectivity, and observation opportunities shaped by physical motion. Evaluating runtime strategies therefore requires assessing whether their decisions fulfill mission objectives, beyond isolated perception accuracy or execution efficiency.”

more of the abstract

We present EmbodiedIntentBench, a benchmark for intent-driven runtime adaptation in mobile robotic missions. It represents mission intent through structured contracts for coverage, temporal evidence, reporting, urgency, and resources, and couples simulated unmanned aerial vehicle (UAV) workloads with causal, resource-accounted execution. Computation decisions affect mission time, resource use, and which observations can contribute evidence. We evaluate fixed and adaptive perception strategies in multi-phase missions and under changing urgency, connectivity, and battery conditions. In the multi-phase Depot study, a configuration with 87.5% full-bank target recall across visible target observations completes only 1 of 16 missions, whereas a lower-recall configuration completes 14. In an ablation, ignoring execution-induced observation loss increases aggregate mission success and reverses the ordering of two runtime strategies. Replays using Jetson AGX Orin CPU and GPU profiles change the relative success of local and remote strategies. In selected Jetson GPU-profile replays, intent-driven adaptation reduces modeled task energy by up to 28% with unchanged mission success. EmbodiedIntentBench provides an extensible framework for evaluating runtime decisions against mission fulfillment under physical and resource constraints.

from the abstract

Pith says

Machine review · deepseek-v4-flash · 10 Nov 2026 · what was read was not recorded · not checked by a person

It can be wrong. Challenge this review or reply to it.

The passes disagreed. Reader: holds up. Skeptic: holds up only with conditions. Referee: minor revision.

Well-built benchmark that cleanly demonstrates perception-accuracy vs. mission-success divergence, but the headline 1/16 vs 14/16 gap rests on a serial blocking execution model whose impact the authors acknowledge without quantifying in that scenario. This line is wrong

2 major objections · 8 minor

How often objections from reviews like this one are right: not yet measured

Are you an author? What you can do.

Not checked: figures, code, what the 54 references say.

The paper says, at §5.1, Table 3

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.66):

“The no-skip protocol is an analytical ablation rather than a realizable parallel-execution implementation.”

Pith says: Objection 1 of 2 · major

The headline result—Mask R-CNN union (87.5% recall) completes 1/16 missions vs. tiled YOLO11s (80.7% recall) completes 14/16—is demonstrated under the serial blocking execution model (Eq. 5). The authors' own causal-execution ablation (Fig. 6b) on the dynamic-urgency study shows that switching to a no-skip protocol reverses the ordering of two strategies, indicating sensitivity to this assumption.

more of objection 1

Because no comparable ablation is performed on the multi-phase Depot study, it is unclear whether the dramatic 1/16 vs. 14/16 gap would shrink or persist under alternative execution models (e.g., asynchronous pipelining). The authors acknowledge the limitation (§2.4, §A.4) but do not quantify its impact on the Depot result. Please provide an ablation for Depot (or at least a clear discussion of bounds on the gap under non-blocking execution) to ensure the central empirical claim is not overstated.

The paper says, at §4.3, Fig. 4b

The review did not quote this passage.

A classifier read this sentence of the paper as acknowledging the concern (probability 0.68):

“These discrep- ancies characterize the uncertainty in quality estimates available to adaptive computation-selection strategies.”

Pith says: Objection 2 of 2 · major

The quality estimates used by the adaptive policies exhibit large errors (e.g., rotated tiled YOLO11s predicted recall 0.007 vs. observed 0.785; CABiNet predicted 0.548 vs. observed 0.000). The paper acknowledges this uncertainty (§4.3), but the adaptive policies rely on these estimates for decision-making.

more of objection 2

Consequently, the finding that adaptive strategies do not outperform fixed best configurations (Sec. 5.1) may partly reflect poor quality estimation rather than an inherent limitation of adaptation. Please clarify the contribution of the estimation method to the adaptive results, and discuss whether alternative quality predictors could change the conclusions about adaptive strategies.

8 minor objections

The paper says, at §2.4, Eq. (5)

Pith says: minor objection 1 of 8

The definition of the next eligible observation uses j = min { k > i | t_k ≥ f_i }. Please clarify whether it is possible that f_i < t_i (completion before the next capture time) and how the model handles this case (e.g., immediate processing of the next capture).

The paper says, at Table 3

Pith says: minor objection 2 of 8

The column header 'Reserve' is ambiguous; consider renaming to 'Battery reserve satisfied' or 'Compliance' for clarity.

show 6 more

The paper says, at Fig. 4(a)

Pith says: minor objection 3 of 8

The dual-scale axis for recall and missions completed is clear, but the font size in the bar labels is small when printed. Increasing the font or providing a supplementary table would improve readability.

The paper says, at Abstract, line [b6]

Pith says: minor objection 4 of 8

The term 'full-bank target recall' is used without definition; consider adding a brief parenthetical explanation (e.g., 'recall over all visible target observations in the precomputed prediction bank').

The paper says, at §4.2

Pith says: minor objection 5 of 8

In the description of resource profiles, the sentence 'Onboard inference is modeled at 15 W' might be clearer if it states that this includes GPU/SOC power for typical embedded platforms, as later referenced.

The paper says, at §5.3

Pith says: minor objection 6 of 8

The caption of Fig. 6 refers to '648 matched policy–condition executions per setting' in panel (a) and '72' in panel (b). The relationship between these numbers (nine policies × 72 conditions = 648) could be explicitly stated for clarity.

The paper says, at Appendix A.4, line [b572]

Pith says: minor objection 7 of 8

The statement 'Predictions, network transfers, loading costs, and downstream budgets remain fixed' when describing latency multipliers is helpful. It may be worth adding that the energy scaling applies only to the modeled local compute energy, not to the remote server or flight energy.

The paper says, at General

Pith says: minor objection 8 of 8

The paper uses 'modeled' for remote execution and network costs throughout; it is clear from context, but a one-sentence reminder in the main text that these are not physically deployed measurements would strengthen reproducibility assurance.

What would settle it

Re-run all 16 Depot multi-phase conditions (Table 3) with the no-skip execution protocol (as defined in §4.4 and used in Fig. 6), which makes all captures available regardless of inference overlap, for both Mask R-CNN union and tiled YOLO11s. If Mask R-CNN union achieves ≥10/16 missions (or the gap to YOLO11s tiled narrows to less than 4 missions), then the headline discrepancy is primarily an artifact of the serial-blocking assumption; if the gap remains large, the result is robust to this variation.

from the skeptic's reading

How the review went

4 readings by deepseek-v4-flash · 10 Nov 2026

  1. Reader holds up confidence high
  2. Skeptic partly agrees: says it holds up only with conditions 28 s · 23,403 tokens read, 2,728 written Multi-phase Depot result (Mask R-CNN union 1/16 vs YOLO11s tiled 14/16) depends on the serial blocking execution model; under an asynchronous/no-skip protocol the gap may shrink, weakening the central claim.
  3. Editor wrote the verdict above 17 s · 24,369 tokens read, 1,659 written
  4. Referee minor revision: 2 major objections, 8 minor 25 s · 23,894 tokens read, 3,106 written

Not run on this paper: the simulated authors' defence.

Pith did not check this review's objections against the paper.

The review in full

The review in brief, machine-written

The paper delivers a genuinely useful benchmark framework and a clear empirical point: perception accuracy alone is a poor proxy for mission success when computation delays cause observation loss. The Depot result—Mask R-CNN union at 87.5% recall completing 1 of 16 missions while tiled YOLO11s at 80.7% recall completes 14—is eye-catching and the authors back it with controlled replay, multiple ablations, and honest limitation statements. That alone makes this worth reading for anyone building runtime adapters for mobile robots.

The soft spot is the one the stress-test note flags. The dramatic gap depends on the serial blocking execution model (Eq. 5), where high-latency inferences skip most captures. The authors' own no-skip ablation in the dynamic study reverses strategy rankings, but they did not run that ablation on the Depot multi-phase scenario where the headline number lives. They acknowledge the limitation in §2.4 and §A.4, but the central evidence for the paper's most striking claim is therefore conditional on an assumption that real systems often avoid via pipelining or parallel inference. I don't think this undermines the broader conclusion—latency still matters, mission success still diverges from frame-level recall—but it does mean the 1/16 vs 14/16 ratio is not a robust fact about those perception models in realistic deployments. It is a fact about those models under one particular, consequential execution policy.

A secondary concern: the quality estimators used by adaptive policies are quite poor (rotated tiled YOLO11s predicted recall 0.007 vs observed 0.785; CABiNet predicted 0.548 vs observed 0.0). That limits what we can conclude about the adaptive strategies' effectiveness, and the paper could say more about the implications.

Overall: solid engineering, clean evaluation, useful framework. The central insight holds. The headline number is real but fragile, and the authors are honest about its scope. This deserves a serious peer review—the framework is publishable, and the limitations are discussable rather than fatal.

The strongest objection

The paper's headline result—that a configuration with 87.5% recall completes only 1/16 missions while one with 80.7% recall completes 14/16—rests on the serial blocking execution model (Eq. 5, §2.4). In this model, high-latency inference (e.g., Mask R-CNN union at 6.91 s) skips most captures (only ~1 in 4 processed), directly causing observation loss. The authors' own dynamic-study ablation (Fig. 6b) shows that switching to a no-skip protocol reverses the ordering of two strategies, confirming sensitivity to this assumption. However, that ablation was performed only on the dynamic-urgency study, not on the multi-phase Depot and Lake scenarios where the strongest numerical result lives. Real mobile robotic systems often use asynchronous pipelines or parallel processing that retain more captures even when inference is slow. If the no-skip protocol were applied to Depot, Mask R-CNN union might process a larger fraction of captures, potentially raising its mission success rate and shrinking the gap to tiled YOLO11s. The central conclusion—that perception accuracy alone mispredicts mission success—could still hold (latency still matters for timeliness), but the dramatic 1/16 vs 14/16 gap might vanish, undercutting the paper's most striking evidence. The authors acknowledge the limitation (§2.4, §A.4) but do not quantify its impact on the multi-phase result.

The reader correctly identifies the serial blocking model as the weakest assumption. However, the reader still accepts the paper, apparently satisfied that the limitation is acknowledged. In my view, the multi-phase result is the paper's central empirical showpiece; its dependence on a specific (and arguably non-representative) execution model is a load-bearing concern that warrants a conditional verdict. A CONDITIONAL verdict would require the authors to either demonstrate robustness via the proposed test or explicitly bound the effect. The reader's argument about generality to real hardware is orthogonal; the concern here is about the benchmark's internal logic, not external validity. The concrete test directly checks whether the striking 1/16 vs 14/16 contrast survives under a more permissive execution model. If it does not, the paper's strongest claim weakens. Hence a conditional acceptance is more appropriate than unconditional acceptance.

The referee's report

If the results hold, EmbodiedIntentBench provides a principled and extensible methodology for evaluating runtime computation decisions against explicit mission objectives, moving beyond isolated perception accuracy or execution efficiency. The benchmark's causal execution model captures a critical coupling between computation latency and observation availability that is often overlooked. The empirical demonstrations show that high-recall perception can lead to very poor mission outcomes due to missed observations, and that resource conditions and connectivity significantly affect strategy effectiveness. This could influence how robotic sensing systems are designed and assessed, particularly in time-critical and resource-constrained applications. The benchmark is accompanied by publicly released code and data for the dynamic study, enhancing reproducibility.

Pith's reading of the paper (a machine's summary, not the authors')

This paper argues that mission success in mobile robotic missions cannot be predicted from perception accuracy alone, because computation delays causally reduce the number of observations that can be processed during physical motion. The authors present EmbodiedIntentBench, a benchmark that connects structured mission contracts (covering evidence, timing, reporting, and resources) with causal, resource-accounted execution over recorded UAV trajectories. Their experiments show that a high-recall but slow configuration (Mask R-CNN union) completes only 1 of 16 missions, while a faster, lower-recall configuration (tiled YOLO11s) completes 14. An ablation reveals that ignoring computation-induced observation loss overestimates mission success and reverses the ordering of runtime strategies. The benchmark demonstrates that runtime evaluation must account for how computation timing affects observation availability and cumulative mission evidence.

What carries the argument. Two mechanisms carry the argument. (1) Causal, resource-accounted execution (Eq. 5): a logical execution clock advances with processing, and the next eligible observation is the first capture whose timestamp falls at or after the completion time of the current blocking processing interval. This serial model captures how latency causes observation loss. (2) Structured mission contract (Eq. 1): a JSON-based specification of goals (coverage, repeated confirmation, fresh revisits), temporal constraints (deadlines per request and phase), reporting obligations (correct and unique reports, false-detection limits), and resource limits (battery reserve, communication). Together they enable evaluation of whether accumulated evidence and reports satisfy the intended mission under physical and resource constraints.

Core claim. The central claim is that mission-level success in mobile robotic sensing is decoupled from frame-level perception accuracy due to the causal effect of computation latency on observation availability. In the multi-phase Depot study, the authors compare nine fixed perception configurations over 16 mission conditions. Mask R-CNN union achieves the highest full-bank target recall (0.875) but completes only 1 of 16 missions, while tiled YOLO11s (0.807 recall) completes 14 missions. The high-latency configuration (6.91 s inference) processes roughly one in four observation opportunities under a two-second capture interval, limiting the evidence available for phase completion. Further, ignoring execution-induced observation loss by switching to a no-skip counterfactual increases aggregate mission success and reverses the relative ordering of quality-aware routing and fixed remote execution, confirming that causal observation accounting is essential for fair strategy comparison.

The premise it rests on. The benchmark assumes a serial, blocking execution model where perception processing prevents subsequent observations from being processed during that interval; if real systems use asynchronous pipelining or parallel processing that can absorb more observations, the observed tradeoffs between latency and observation loss could change.

If the paper is right (Pith's inferences, not the authors')

Runtime adaptation strategies for UAV sensing should be evaluated under causal execution rather than assuming all observations are available; otherwise mission success may be overestimated and strategy rankings may be reversed.

High-accuracy but slow perception models can be detrimental to mission success in time-sensitive tasks, even when they improve individual predictions, because they cause observation loss.

Intent-driven adaptation (stopping perception when the required number of reports is already obtained) can reduce onboard energy consumption by up to 28% without reducing mission success on selected embedded profiles.

The benchmark's diagnostic measures (phase completion, evidence pipeline breakdown, requirement-level failure attribution) make it possible to identify whether a strategy fails due to insufficient evidence, untimely execution, reporting deficiencies, or resource violations.

The same decoupling between perception accuracy and mission success likely applies to other mobile robotic platforms (ground vehicles, underwater robots) where observation opportunities are shaped by physical motion and computation latency. Recasting existing benchmarks with causal execution could reveal similar overestimates of mission viability.

Although the benchmark uses a serial blocking execution model, even asynchronous pipelines with bounded buffers may exhibit observation loss if downstream stages cannot keep up with capture rate; the paper's ablation suggests that the serial model is a conservative bound that may still capture the dominant effect in constrained systems.

The fixed-trajectory methodology isolates computation effects, but in closed-loop systems, navigation decisions could compensate for or exacerbate observation loss. An extension to closed-loop control could test whether the accuracy–success decoupling persists when the UAV can alter its path to reacquire missed observations.

Check this review

Pith stored no record of this review's passes and took no fingerprint of it. Reviews made by code from 13 Nov 2026 on carry both.

How often reviews like this one are right

Reviews like this one: written by deepseek-v4-flash, where what was read was not recorded.

How often objections from reviews like this one are right: not yet measured

Every value above, in the review's public record (JSON)

Reviews by people

This review was written by a machine. No person has reviewed this paper on Pith yet. A scientist listed on Pith can review it for a fee, and their review is published here whatever it concludes.

Request a human review

How Pith checks papers · The full audit of this paper

The paper

Abstract

Mobile robotic sensing systems must adapt to operator requirements, limited resources, changing connectivity, and observation opportunities shaped by physical motion. Evaluating runtime strategies therefore requires assessing whether their decisions fulfill mission objectives, beyond isolated perception accuracy or execution efficiency. We present EmbodiedIntentBench, a benchmark for intent-driven runtime adaptation in mobile robotic missions. It represents mission intent through structured contracts for coverage, temporal evidence, reporting, urgency, and resources, and couples simulated unmanned aerial vehicle (UAV) workloads with causal, resource-accounted execution. Computation decisions affect mission time, resource use, and which observations can contribute evidence. We evaluate fixed and adaptive perception strategies in multi-phase missions and under changing urgency, connectivity, and battery conditions. In the multi-phase Depot study, a configuration with 87.5% full-bank target recall across visible target observations completes only 1 of 16 missions, whereas a lower-recall configuration completes 14. In an ablation, ignoring execution-induced observation loss increases aggregate mission success and reverses the ordering of two runtime strategies. Replays using Jetson AGX Orin CPU and GPU profiles change the relative success of local and remote strategies. In selected Jetson GPU-profile replays, intent-driven adaptation reduces modeled task energy by up to 28% with unchanged mission success. EmbodiedIntentBench provides an extensible framework for evaluating runtime decisions against mission fulfillment under physical and resource constraints.

The paper's own sentences, arranged, kept beside the review and separate from it. Each label is drawn from a closed vocabulary; the number beside it is the probability the classifier gave that label. No sentence in this record was written by a model.

abstract compiled · 2026-11-10

The authors' main claim, as the classifier picked it out 0.60

“EmbodiedIntentBench provides an extensible framework for evaluating runtime decisions against mission fulfillment under physical and resource constraints.”

How the main claim is stated: asserted 1.00

What the abstract itself states, as probabilities: claims first 0.07 · states limitation 0.33 · human participants 0.05 · controlled comparison 0.71 · randomized assignment 0.02 · states quantitative result 0.99 · compares with prior results 0.79 · mentions code or data availability 0.07

The abstract, sentence by sentence

This table labels the abstract only (arXiv listing abstract v1). The number is the probability the classifier gave the label.

SentenceRoleThe authors' own workStates the main conclusionStrength
Mobile robotic sensing systems must adapt to operator requirements, limited resources, changing connectivity, and observation opportunities shaped by physical motion. background 1.00 0.06 0.02 asserted 1.00
Evaluating runtime strategies therefore requires assessing whether their decisions fulfill mission objectives, beyond isolated perception accuracy or execution efficiency. background 0.71 0.08 0.07 asserted 0.97
We present EmbodiedIntentBench, a benchmark for intent-driven runtime adaptation in mobile robotic missions. contribution 1.00 0.92 0.08 asserted 1.00
It represents mission intent through structured contracts for coverage, temporal evidence, reporting, urgency, and resources, and couples simulated unmanned aerial vehicle (UAV) workloads with causal, resource-accounted execution. method 0.61 0.89 0.07 asserted 1.00
Computation decisions affect mission time, resource use, and which observations can contribute evidence. background 0.77 0.21 0.05 asserted 1.00
We evaluate fixed and adaptive perception strategies in multi-phase missions and under changing urgency, connectivity, and battery conditions. method 0.85 0.93 0.04 asserted 0.95
In the multi-phase Depot study, a configuration with 87.5% full-bank target recall across visible target observations completes only 1 of 16 missions, whereas a lower-recall configuration completes 14. result 1.00 0.94 0.16 asserted 1.00
In an ablation, ignoring execution-induced observation loss increases aggregate mission success and reverses the ordering of two runtime strategies. result 0.99 0.95 0.10 asserted 1.00
Replays using Jetson AGX Orin CPU and GPU profiles change the relative success of local and remote strategies. result 0.98 0.93 0.04 asserted 1.00
In selected Jetson GPU-profile replays, intent-driven adaptation reduces modeled task energy by up to 28% with unchanged mission success. result 1.00 0.95 0.16 asserted 0.99
EmbodiedIntentBench provides an extensible framework for evaluating runtime decisions against mission fulfillment under physical and resource constraints. contribution 0.87 0.66 0.49 asserted 1.00

What kind of paper the classifier reports this is: dataset or benchmark 1.00 · evidence from simulation or computation 0.97

What was examined, and what was not

Sources read

  • arXiv listing abstract v1

Not examined

  • full text
  • figures and tables
  • references and citing sentences
  • relations to other papers

Levels run

  • P abstract

Not run

  • S sections
  • T body sentences
  • C citations
  • R cross-paper relations

How the labels were made

Compiled by classifier-1.13.0 via TypeSafe API, question bank abstract-p1-20260923, 2026-11-10: 1 request, 8,157 input tokens.

Every quoted sentence on this record is the authors'. Every label is from Pith's closed vocabulary, with the probability shown beside it. This record as JSON

Figures (6)
Figure 1 of the paper
Figure 1. Motivation and overview of EmbodiedIntentBench. (a) Operator￾specified missions impose requirements for target coverage, evidence ver￾ification, timeliness, and resource use. (b) Local, split, and remote execution offer different computation and communication tradeoffs; the current eval￾uation considers whole-model local and remote execution. (c) Perception quality and execution latency influence mission evidence, as longer process￾ing times can prevent subsequent observations from being processed. (d) EmbodiedIntentBench connects structured mission requirements with physi￾cally…
Figure 2 of the paper
Figure 2. Architecture of EmbodiedIntentBench. (a) Intent specification: An operator request ( 1 ) is represented through a structured mission contract ( 2 ) defining evidence, temporal, reporting, and resource requirements. (b) Mission workloads and runtime decisions: Physically situated observations ( 3 ) and current system state inform a runtime policy ( 4 ) that selects a computation configuration. (c) Causal execution and resource accounting: A resource-accounted executor ( 5 ) applies the selected computation and its associated costs, while the execution clock and resource state ( 6 )…
Figure 3 of the paper
Figure 3. Physical workloads and mission scenarios in
Figure 4 of the paper
Figure 4. Perception quality and mission fulfillment across nine configurations in Depot. (a) Full-bank target recall and completed missions for fixed perception
Figure 5 of the paper
Figure 5. Runtime adaptation under changing urgency and resource conditions.
Figure 6 of the paper
Figure 6. Impact of causal execution on mission outcomes and runtime strat

Figures are the authors', reproduced from the paper.

References (54)
  1. [1] Rajat Bhattacharjya, Sing-Yao Wu, Hyunwoo Oh, Chaewon Nam, Suyeon Koo, Mohsen Imani, Elaheh Bozorgzadeh, and Nikil Dutt. AVERY: Intent-driven adaptive VLM split computing via embodied self-awareness for efficient disaster response systems.arXiv preprint arXiv:2511.18151, 2025 on PitharXiv
  2. [2] Fernando Cladera, Zachary Ravichandran, Jason Hughes, Varun Murali, Car- los Nieto-Granda, M Ani Hsieh, George J Pappas, Camillo J Taylor, and Vijay Kumar. Air-ground collaboration for language-specified missions in unknown environments.IEEE Transactions on Field Robotics, 2:6... on Pith
  3. [3] Reza Farahani, Zoha Azimi, Ilir Murturi, Arda Goknil, Sagar Sen, Christian Timmerer, and Schahram Dustdar. EVLM: Intent-driven edge vision language model for UAV-based power line inspection. In2026 IEEE International Conference on Edge Computing and Communications (EDGE), page... on Pith
  4. [4] Minghui Zhao, Junxi Xia, Kaiyuan Hou, Yanchen Liu, Stephen Xia, and Xiaofan Jiang. FlexiFly: Interfacing the physical world with foundation models empow- ered by reconfigurable drone systems. InProceedings of the 23rd ACM Conference on Embedded Networked Sensor Systems, SenSys... on Pith
  5. [5] Rajat Bhattacharjya, Yoomee Jung, Minwoo Kim, Sing-Yao Wu, Eli Bozorgzadeh, Nalini Venkatasubramanian, and Nikil Dutt. FloodReasonBench: Benchmarking VLM reasoning segmentation for embodied flood response at the edge.arXiv preprint arXiv:2608.15410, 2026 on PithPith's reviewarXiv
  6. [6] Qitao Weng and Heechul Yun. Multi-resolution end-to-end deep neural net- work for optimizing latency-accuracy tradeoff in autonomous driving. In2026 ACM/IEEE 17th International Conference on Cyber-Physical Systems (ICCPS), pages 12–18. IEEE, 2026 on Pith
  7. [7] Jingxian Chen, Yukai Song, Shengjie Xu, Kyle Kessler, Prateek Ganguli, Arkaprava Gupta, Bineet Ghosh, Parasara Sridhar Duggirala, Tianlong Chen, Samarjit Chakraborty, et al. Controller-aware perception neural network prun- ing for cps safety optimization.ACM Transactions on Cy... on Pith
  8. [8] Ahmet Soyyigit, Shuochao Yao, and Heechul Yun. MURAL: A multi-resolution anytime framework for LiDAR object detection deep neural networks. In2025 IEEE 31st International Conference on Embedded and Real-Time Computing Systems and Applications (RTCSA), pages 33–43. IEEE, 2025 on Pith
  9. [9] Jingfei Xia, Yuze He, Chen Bian, Zhenyu Yan, and Guoliang Xing. EventEye: Towards high-frequency perception enhancement for autonomous vehicles using infrastructure-mounted event cameras. InProceedings of the 2026 ACM/IEEE International Conference on Embedded Artificial Intell... on Pith
  10. [10] Hyunseung Kim, Sheetal Prasanna, Yin Li, Somali Chaterji, and Saurabh Bagchi. ApproxBit: Efficient video analytics through latency-aware offloading with learned binary codes. InProceedings of the 2026 ACM/IEEE International Confer- ence on Embedded Artificial Intelligence and ... on Pith
  11. [11] Zoha Azimi, Reza Farahani, Schahram Dustdar, and Christian Timmerer. Cloud, edge, or split? profiling onboard and split vision-language model deployment for drone ai.arXiv preprint arXiv:2609.25415, 2026 on PithPith's reviewarXiv
  12. [12] David Candal-Ventureira, Francisco Javier González-Castaño, Felipe Gil- Castiñeira, and Pablo Fondo-Ferreiro. Is the edge really necessary for drone computing offloading? an experimental assessment in carrier-grade 5G operator networks.Software: Practice and Experience, 53(3):... on Pith
  13. [13] Mihir Bala, Aditya Chanana, Xiangliang Chen, Qifei Dong, Thomas Eiszler, Jingao Xu, Padmanabhan Pillai, and Mahadev Satyanarayanan. The OODA loop of cloudlet-based autonomous drones. In2024 IEEE/ACM Symposium on Edge Computing (SEC), pages 178–190, 2024 on Pith
  14. [14] Behzad Boroujerdian, Hasan Genc, Srivatsan Krishnan, Wenzhi Cui, Aleksandra Faust, and Vijay Reddi. MAVBench: Micro aerial vehicle benchmarking. In2018 51st annual IEEE/ACM international symposium on microarchitecture (MICRO), pages 894–907. IEEE, 2018 on Pith
  15. [15] Víctor Mayoral-Vilches, Jason Jabbour, Yu-Shun Hsiao, Zishen Wan, Martiño Crespo-Álvarez, Matthew Stewart, Juan Manuel Reina-Muñoz, Prateek Nagras, Gaurav Vikhe, Mohammad Bakhshalipour, Martin Pinzger, Stefan Rass, Smruti Panigrahi, Giulio Corradi, Niladri Roy, Phillip B. Gibb... on Pith
  16. [16] Ikechukwu Uchendu, Jason Jabbour, Korneel Van den Berghe, Joel Runevic, Matthew Stewart, Jeffrey Ma, Srivatsan Krishnan, Izzeddin Gur, Austin Huang, Colton Bishop, Paige Bailey, Joe Wenjie Jiang, Ebrahim M. Songhori, Sergio Guadarrama, Jie Tan, Jordan K. Terry, Aleksandra Faus... on Pith
  17. [17] Mengtian Li, Yu-Xiong Wang, and Deva Ramanan. Towards streaming perception. InEuropean conference on computer vision, pages 473–488. Springer, 2020 on Pith
  18. [18] Jinrong Yang, Songtao Liu, Zeming Li, Xiaoping Li, and Jian Sun. Real-time object detection for streaming perception. InProceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, pages 5385–5395, 2022 on Pith
  19. [19] Rowan McAllister, Blake Wulfe, Jean Mercat, Logan Ellis, Sergey Levine, and Adrien Gaidon. Control-aware prediction objectives for autonomous driving. In 2022 International Conference on Robotics and Automation (ICRA). IEEE, 2022 on Pith
  20. [20] Hoang Pham Cong and Ho Viet Duc Luong. The decision value of perception compute.arXiv preprint arXiv:2609.35910, 2026 on PithPith's reviewarXiv
show 34 more
  1. [21] Shaojie Ren, Jingwen Sun, Zezhi Liu, Hongjin Chen, Xin Jin, Wei Zou, and Zhibo Chen. LIBERO-Dynamic: Benchmarking robotic manipulation in dynamic environments.arXiv preprint arXiv:2610.24579, 2026 on PithPith's reviewarXiv
  2. [22] Nathan Koenig and Andrew Howard. Design and use paradigms for gazebo, an open-source multi-robot simulator. In2004 IEEE/RSJ international conference on intelligent robots and systems (IROS)(IEEE Cat. No. 04CH37566), volume 3, pages 2149–2154. Ieee, 2004 on Pith
  3. [23] Yoshitomo Matsubara, Marco Levorato, and Francesco Restuccia. Split computing and early exiting for deep learning applications: Survey and research challenges. ACM Computing Surveys, 55(5):1–30, 2022 on Pith
  4. [24] Rajat Bhattacharjya, Minwoo Kim, Arnab Sarkar, Tamoghno Das, Sing-Yao Wu, Eli Bozorgzadeh, Marco Levorato, and Nikil Dutt. Freshlatent: Channel-aware latent adaptation for resource-constrained embodied vlm perception.arXiv preprint arXiv:2609.30629, 2026 on PithPith's reviewarXiv
  5. [25] Open Robotics. Gazebo Harmonic documentation. https://gazebosim.org/docs/h armonic/. Accessed: November 3, 2026 on Pith
  6. [26] Rafi Abdullah and Louise Poubel. Depot. https://fuel.gazebosim.org/1.0/OpenR obotics/models/Depot. Accessed: November 3, 2026 on Pith
  7. [27] Cole Biesemeyer. Harmonic Terrain. https://fuel.gazebosim.org/1.0/OpenRobot ics/models/Harmonic%20Terrain. Accessed: November 3, 2026 on Pith
  8. [28] Cole Biesemeyer. Harmonic Terrain Objects. https://fuel.gazebosim.org/1.0/O penRobotics/models/Harmonic%20Terrain%20Objects. Accessed: November 3, 2026 on Pith
  9. [29] Cole Biesemeyer. Lake House. https://fuel.gazebosim.org/1.0/OpenRobotics/mo dels/Lake%20House. Accessed: November 3, 2026 on Pith
  10. [30] OpenRobotics. Coast Waves 2. https://fuel.gazebosim.org/1.0/OpenRobotics/mo dels/Coast%20Waves%202. Accessed: November 3, 2026 on Pith
  11. [31] National Search and Rescue Council.National Search and Rescue Manual: Volume 2—Search and Rescue Operations. Australian Maritime Safety Authority, 2026. Accessed: November 3, 2026 on Pith
  12. [32] Kaiming He, Georgia Gkioxari, Piotr Dollár, and Ross Girshick. Mask R-CNN. InProceedings of the IEEE International Conference on Computer Vision, pages 2961–2969, 2017 on Pith
  13. [33] TorchVision Contributors. TorchVision: Mask r-cnn with resnet-50-fpn v2. https://docs.pytorch.org/vision/main/models/generated/torchvision.models.d etection.maskrcnn_resnet50_fpn_v2.html. Accessed: November 3, 2026 on Pith
  14. [34] Glenn Jocher and Jing Qiu. Ultralytics YOLO11. docs.ultralytics.com/models/yolo11, 2024. Accessed: November 3, 2026 on Pith
  15. [35] Saumya Kumaar, Ye Lyu, Francesco Nex, and Michael Ying Yang. CABiNet: Efficient context aggregation network for low-latency semantic segmentation. In2021 IEEE International Conference on Robotics and Automation, pages 13517– 13524, 2021 on Pith
  16. [36] Ye Lyu, George Vosselman, Gui-Song Xia, Alper Yilmaz, and Michael Ying Yang. UAVid: A semantic segmentation dataset for UAV imagery.ISPRS Journal of Photogrammetry and Remote Sensing, 165:108–119, 2020 on Pith
  17. [37] dronefreak. CABiNet (MobileNetV3-Small) Finetuned on UAVid. https://huggin gface.co/dronefreak/cabinet-mobilenetv3-small-uavid. Accessed: November 3, 2026 on Pith
  18. [38] DJI. DJI Mini 4 Pro: Specifications. https://www.dji.com/mini-4-pro/specs. Accessed: November 3, 2026 on Pith
  19. [39] Krzysztof Falkowski and Michał Duda. Dynamic models identification for kine- matics and energy consumption of rotary-wing uavs during different flight states. Sensors, 23(23):9378, 2023. Accessed: November 3, 2026 on Pith
  20. [40] NVIDIA. Jetson TX2 Module: Technical specifications. https://developer.nvidia .com/embedded/jetson-tx2. Accessed: November 3, 2026 on Pith
  21. [41] New Jersey Department of Environmental Protection.sUAS Flight Operations Manual. New Jersey Department of Environmental Protection, 2020 on Pith
  22. [42] Autel Robotics. EVO Max Smart Flight Battery. https://shop.autelrobotics.com /products/evo-max-smart-flight-battery. Accessed: November 3, 2026. 13 Bhattacharjya et al on Pith
  23. [43] Ran Xu, Chen lin Zhang, Pengcheng Wang, Jayoung Lee, Subrata Mitra, Somali Chaterji, Yin Li, and Saurabh Bagchi. ApproxDet: Content and contention- aware approximate object detection for mobiles. InProceedings of the 18th ACM Conference on Embedded Networked Sensor Systems. ACM, 2020 on Pith
  24. [44] Srivatsan Krishnan, Behzad Boroujerdian, William Fu, Aleksandra Faust, and Vijay Janapa Reddi. Air Learning: A Deep Reinforcement Learning Gym for Autonomous Aerial Robot Visual Navigation.Machine Learning, 110:2501–2540, 2021 on Pith
  25. [45] Xiangyu Wang, Donglin Yang, Ziqin Wang, Hohin Kwan, Jinyu Chen, Wenjun Wu, Hongsheng Li, Yue Liao, and Si Liu. Towards Realistic UAV Vision-Language Navigation: Platform, Benchmark, and Methodology. arXiv:2410.07087, 2024 on PithPith's reviewarXiv
  26. [46] Mingning Guo, Mengwei Wu, Jiarun He, Shaoxian Li, Haifeng Li, and Chao Tao. BEDI: A Comprehensive Benchmark for Evaluating Embodied Agents on UAVs. ISPRS Journal of Photogrammetry and Remote Sensing, 232:910–936, 2026 on Pith
  27. [47] Mohamed Amine Ferrag, Abderrahmane Lakas, and Mérouane Debbah. UAVBench: An Open Benchmark Dataset for Autonomous and Agentic AI UAV Systems via LLM-Generated Flight Scenarios.IEEE Open Journal of Vehicular Technology, 7:2542–2558, 2026 on Pith
  28. [48] Rui Yang, Hanyang Chen, Junyu Zhang, Mark Zhao, Cheng Qian, Kangrui Wang, Qineng Wang, Teja Venkat Koripella, Marziyeh Movahedi, Manling Li, et al. EmbodiedBench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents.arXiv preprint arXi... on PithPith's reviewarXiv
  29. [49] Srivatsan Krishnan, Zishen Wan, Kshitij Bhardwaj, Aleksandra Faust, and Vi- jay Janapa Reddi. Roofline model for uavs: A bottleneck analysis tool for design- ing compute systems for autonomous drones.arXiv preprint arXiv:2111.03792, 2021 on PithPith's reviewarXiv
  30. [50] Zishen Wan, Jiayi Qian, Yuhang Du, Jason Jabbour, Yilun Du, Yang Zhao, Arijit Raychowdhury, Tushar Krishna, and Vijay Janapa Reddi. Generative AI in em- bodied systems: System-level analysis of performance, efficiency and scalability. In2025 IEEE International Symposium on Per... on Pith
  31. [51] Jirong Zha, Yuxuan Fan, Tianyu Zhang, Geng Chen, Yingfeng Chen, Chen Gao, and Xinlei Chen. AirCopBench: A benchmark for multi-drone collaborative embodied perception and reasoning.Proceedings of the AAAI Conference on Artificial Intelligence, 40(2):1507–1515, 2026 on Pith
  32. [52] Anurag Ghosh, Vaibhav Balloli, Akshay Nambi, Aditya Singh, and Tanuja Ganu. Chanakya: Learning runtime decisions for adaptive real-time perception.Ad- vances in Neural Information Processing Systems, 36:55668–55680, 2023 on Pith
  33. [53] Rajat Bhattacharjya, Arnab Sarkar, Ish Kool, Sabur Baidya, and Nikil Dutt. Access- av: Adaptive communication-computation codesign for sustainable autonomous vehicle localization in smart factories.ACM Trans. Embed. Comput. Syst., 25(1), January 2026 on Pith
  34. [54] Rajat Bhattacharjya, Hyeonjong Ju, Sing-Yao Wu, Eli Bozorgzadeh, and Nikil Dutt. MemoGuard: An adaptive runtime for guarding against memory traps in communication-limited robot navigation.IEEE Embedded Systems Letters, 18(5):447–451, 2026. 14 EmbodiedIntentBench: Benchmarking ... on Pith

Challenges and discussion

Disagree with the review, or know something it missed? Leave a comment, or challenge this review formally: a challenge becomes a permanent entry in this paper's record, and its decision is published here.

No comments yet.

Sign in to comment