{"total":33,"items":[{"citing_arxiv_id":"2606.31471","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Think While You Map: Asynchronous Vision-Language Agents for Incremental 3D Scene Graphs","primary_cat":"cs.CV","submitted_at":"2026-06-30T10:49:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An asynchronous architecture decouples incremental voxel-based mapping from VLM-based semantic enrichment to produce queryable open-vocabulary 3D scene graphs that match or exceed prior methods on segmentation and grounding benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.28617","ref_index":3,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"A Fast Convergent Algorithm for Solving Non-convex Partially-Decoupled Generalized Nash Equilibrium Problems","primary_cat":"cs.MA","submitted_at":"2026-06-26T21:26:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"FALCON algorithm solves non-convex partially-decoupled GNEPs via SCP and potential games, claiming global convergence to open-loop Nash equilibria under mild assumptions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.26780","ref_index":39,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Event-based Gaze Control System for Accurate Real-time Spin Estimation in Professional Ball Games","primary_cat":"cs.CV","submitted_at":"2026-06-25T09:14:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"An event-camera system with active gaze control and contrast-maximization spin estimation achieves real-time performance in table tennis with 8.8% magnitude error, 6.4° axis error, 3 ms latency, and 750 Hz throughput.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.25699","ref_index":15,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"SA-LIVO: Efficient LiDAR-Inertial-Visual Odometry with Subspace-Aware Degeneracy Handling","primary_cat":"cs.RO","submitted_at":"2026-06-24T11:13:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"SA-LIVO uses eigendecomposition of the joint information matrix with linear-clamp soft gates per eigendirection for efficient degeneracy-aware LiDAR-inertial-visual odometry.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.23046","ref_index":32,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"UECP: Uncertainty-Enhanced Collaborative Perception","primary_cat":"cs.CV","submitted_at":"2026-06-22T08:55:10+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"UECP replaces detection-correlated confidence maps with a LiDAR point-density uncertainty map and introduces Uncertainty-Aware Pyramid Fusion to improve collaborative perception.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.22113","ref_index":32,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"KITE: Decoupling Kinematics and Interaction for Zero-Shot Cross-Embodiment Manipulation","primary_cat":"cs.RO","submitted_at":"2026-06-20T15:51:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"KITE decouples task reasoning from embodiment-specific control via learned latent interaction intents to enable zero-shot transfer across structurally different robots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.21205","ref_index":36,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Discrete Geometric Modeling and Extended State Estimation of Continuum Robots","primary_cat":"eess.SY","submitted_at":"2026-06-19T08:17:32+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A fully discrete strain-based model for continuum robot dynamics via Lie group variational integrators, combined with an EKF-based observer for states and disturbances, validated on hardware.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.20239","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Optimizing Agricultural Drone Operations: From Launch and Recovery Siting to Tiered Routing Strategies","primary_cat":"math.OC","submitted_at":"2026-06-18T13:49:44+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"p-median heuristic for facility siting and 6-8 cluster tiered routing reduce drone operation planning time by 1-3 orders of magnitude with 4% or less loss in serviced area.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2606.08666","ref_index":5,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Language as a Sensor: Calibrated Spatial Belief Estimation in 3D Scenes from Natural Language","primary_cat":"cs.RO","submitted_at":"2026-06-07T15:17:25+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Introduces LSM that outputs calibrated multimodal spatial distributions from language plus scene graph, fused via VL-Map to improve 3D target localization on VLA-3D benchmark and real robot.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.31460","ref_index":58,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"On-Device Robotic Planning: Eliminating Inference Redundancy for Efficient Decision-Making","primary_cat":"cs.RO","submitted_at":"2026-05-29T15:51:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"REIS reduces inference redundancy in embodied robotic planning via lightweight gating and routing while preserving task performance on ALFRED and real robots.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.17927","ref_index":12,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Learning-Based Adaptive Control for Surgical Robotic Exposure Task on Deformable Tissues","primary_cat":"cs.RO","submitted_at":"2026-05-18T06:36:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"A simulation-trained deep deformation model combined with online adaptive control enables zero-shot autonomous tissue retraction for ROI exposure in robotic surgery.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.13442","ref_index":7,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Asymptotically Optimal Ergodic Coverage on Generalized Motion Fields","primary_cat":"cs.RO","submitted_at":"2026-05-13T12:37:27+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A flow-adaptive ergodic coverage formulation using MMD that preserves guarantees over evolving domains and supports open-loop planning for robots in flows.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"phasis on wide-spread coverage in the info-max algorithm results in revisitation of previously-seen areas, resulting in sub- optimal performance. The energy-optimal solver performed mildly worse than the info-max approach due to its numer- ical stability's reliance on the satisfaction of the Courant- Friedrichs-Lewy condition, which cannot be guaranteed in all flow-subjected environments [7]. Additionally, the feedback policy of this method defines its displacement as a full thrust along the policy gradient, leading to coarse trajectories that may overshoot and miss high-value regions [19]. In contrast, the flow-adaptive ergodic planner produces smooth, dynamically-consistent trajectories resulting in a total flow discrepancy reduction of 18."},{"citing_arxiv_id":"2605.12735","ref_index":137,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Unified Autonomy Stack: Toward a Blueprint for Generalizable Robot Autonomy","primary_cat":"cs.RO","submitted_at":"2026-05-12T20:39:35+00:00","verdict":"ACCEPT","verdict_confidence":"MODERATE","novelty_score":4.0,"formal_verification":"none","one_line_summary":"An open-sourced Unified Autonomy Stack fuses LiDAR, radar, vision and inertial data with sampling-based planning and control barrier functions to deliver resilient autonomy on aerial and ground robots in challenging real-world settings.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.11714","ref_index":7,"ref_count":9,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Introducing Environmental Constraints to Grasping Strategies for Paper-Like Flexible Materials Using a Soft Gripper","primary_cat":"cs.RO","submitted_at":"2026-05-12T08:03:04+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"Systematic grasping strategies for paper-like materials are developed and tested with a soft gripper by exploiting environmental constraints to improve force control and success rates.","context_count":3,"top_context_role":"background","top_context_polarity":"background","context_text":"Table contact Wall Edge Rigid Flexible This study Grasping Universal soft gripper Jiang et al. [ 13] Singulating Rotatable fingertips Jiang et al. [ 11, 21] Flipping Printed soft gripper Xiong et al. [ 14] Grasping Bistable gripper Zhang et al. [ 26] Prying Rigid two-fingered gripper Turco et al. [ 43] Grasping Soft reconfigurable gripper Yuan et al. [ 32] Grasping Roller-Based hand Morino et al. [ 33] Grasping Sheet-based gripper Ko [ 34] Grasping Tendon-Driven Gripper Babin et al. [ 28, 29] Scooping Passive and epicyclic mechanisms Hang et al. [ 36] Grasping Soft and compliant hands Bimbo et al. [ 37] Grasping Compliant hand Sarantopoulos et al. [ 38] Grasping Rigid three-finger gripper Odhner et al."},{"citing_arxiv_id":"2605.09383","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Safety-Critical LiDAR-Inertial Odometry with On-Manifold Deterministic Protection Level","primary_cat":"cs.RO","submitted_at":"2026-05-10T07:20:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A LiDAR-inertial odometry pipeline using on-manifold ellipsoidal set-membership filtering to output feasible sets as deterministic protection levels under unknown-but-bounded point-cloud noise.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"For two ellipsoidal setsE(a 1,P 1)andE(a 2,P 2) with the same dimension, their intersection is usually not retained as an ellipsoidal set. With the same handling in the Minkowski sum operation, the out-bounding ellipsoidal set (Wang et al., 2022) is required: E(a,P)⊇(E(a 1,P 1)∩ E(a 2,P 2))(6) a=P λ (1−λ)P −1 1 a1 +λP −1 2 a2 \u0001 ,0< λ <1(7) P= (1−ν)P λ (8) where P−1 λ = (1−λ)P −1 1 +λP −1 2 (9) ν= (1−λ)a T 1 P−1 1 a1 +λa T 2 P−1 2 a2 −a TP−1 λ a(10) Additionally, the minimum trace criterion is also used to obtain a unique set, whose solution can be acquired using the linear search methods (Nocedal and Wright, 2018). Similarly, to enhance the clarity, in this paper, the operator ∩E is used to represent the operation of obtaining the optimal"},{"citing_arxiv_id":"2605.09196","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"RigidFormer: Learning Rigid Dynamics using Transformers","primary_cat":"cs.CV","submitted_at":"2026-05-09T22:31:09+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"RigidFormer learns mesh-free rigid dynamics from point clouds using object-centric anchors, Anchor-Vertex Pooling, Anchor-based RoPE, and differentiable Kabsch alignment to enforce rigidity.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Advances in neural information processing systems, 30, 2017. [38] Chen Wang, Roberto Martín-Martín, Danfei Xu, Jun Lv, Cewu Lu, Li Fei-Fei, Silvio Savarese, and Yuke Zhu. 6-PACK: Category-level 6D pose tracker with anchor-based keypoints. In2020 IEEE International Conference on Robotics and Automation (ICRA), pages 10059-10066. IEEE, 2020. doi: 10.1109/ICRA40945.2020.9196679. [39] Qianqian Wang, Yen-Yu Chang, Ruojin Cai, Zhengqi Li, Bharath Hariharan, Aleksander Holynski, and Noah Snavely. Tracking everything everywhere all at once. InProceedings of the IEEE/CVF International Conference on Computer Vision, pages 19795-19806, 2023. [40] Amaury Wei and Olga Fink. Integrating physics and topology in neural networks for learning"},{"citing_arxiv_id":"2605.07041","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Dr-BA: Separable Optimization for Direct Radar Bundle Adjustment & Localization","primary_cat":"cs.RO","submitted_at":"2026-05-07T23:41:16+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Dr-BA delivers a separable optimization approach for direct radar bundle adjustment and cross-session localization using full spinning-radar intensity images, achieving state-of-the-art performance on over 200 km of on-road data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.20348","ref_index":8,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Bimanual Robot Manipulation via Multi-Agent In-Context Learning","primary_cat":"cs.RO","submitted_at":"2026-04-22T08:51:07+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.14652","ref_index":43,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"DigiForest: Digital Analytics and Robotics for Sustainable Forestry","primary_cat":"cs.RO","submitted_at":"2026-04-16T05:59:45+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"DigiForest integrates heterogeneous autonomous robots for data collection, automated tree trait extraction, a decision support system for growth forecasting, and autonomous harvesters for selective logging, with real-world tests in European forests.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"The system performs sensor fusion of relative pose displacements from LiDAR using the ICP algorithm [3], aided by preintegrated IMU measurements [15]. We calibrated the cameras, as well as Camera-IMU extrinsics using the Kalibr tool [20]. In addition, we developed a method for calibration LiDAR and camera using a checkerboard [18]. The factor graph-based LiDAR SLAM system from [43] is used to obtain a consistent estimate of the robot pose in a fixed global frame. Our SLAM system incrementally builds a pose graph, detects loop closure candidates within a radius of 10-15 m from the robot, and optimizes the pose graph in an incremental fashion using the iSAM2 algorithm [26]. We implemented a local sub-mapping module to accumulate all the incoming"},{"citing_arxiv_id":"2604.12667","ref_index":64,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Safe reinforcement learning with online filtering for fatigue-predictive human-robot task planning and allocation in production","primary_cat":"cs.AI","submitted_at":"2026-04-14T12:38:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PF-CD3Q uses online particle filtering to estimate fatigue parameters and constrains a deep Q-learning agent to solve fatigue-aware human-robot task planning as a CMDP.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"However, this second-order mechanism is computationally expensive and highly sensitive to training noiseinnon-convexenvironments,leadingtoinstabilityand eventual divergence during training. Lagrangian methods [61, 64] convert constrained problems into unconstrained ones using Lagrange multipliers, though they can be unstable. To improve this, Stooke et al. [64] introduced a PID Lagrangian approach, enhancing stability through control-theoretic adjustments. Penalty-based methods like IPO [45] add barrier functions to reduce violations. However, the above optimization-based methods may still violate constraints in the training and deployment stage, achieving approximate constraint satisfaction [26]. Knowledge-utilization methods enhance safety by"},{"citing_arxiv_id":"2604.12239","ref_index":20,"ref_count":2,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Physics-Grounded Monocular Vehicle Distance Estimation Using Standardized License Plate Typography","primary_cat":"cs.CV","submitted_at":"2026-04-14T03:27:44+00:00","verdict":null,"verdict_confidence":null,"novelty_score":null,"formal_verification":null,"one_line_summary":null,"context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.05694","ref_index":22,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Foundations of Future Communication Systems: Innovations in Communication - A Report","primary_cat":"cs.IT","submitted_at":"2026-04-07T10:45:24+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":1.0,"formal_verification":"none","one_line_summary":"The report assembles abstracts of invited talks, presentations, and posters from the FFCS conference on foundational limits and emerging paradigms in communication.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"emphasizing decentralized control and robustness [1,62]. Another key focus was on particle swarms controlled by uniform global inputs, where coordinated be- havior emerges through symmetry-breaking mechanisms such as environmental obstacles or boundary friction [20,21,19,8,139]. These techniques enable applica- tions such as targeted drug delivery and micro-scale assembly [22,24]. Subsequently, the presentation addressed scenarios requiring persistent con- nectivity within the swarm, introducing algorithmic strategies that ensure struc- turalintegrityduringreconfiguration[33,64].Finally,anovelapproachtoenergy- efficient tracking of moving objects was presented, based on primal-dual opti- mization methods from mathematical programming [63,111]."},{"citing_arxiv_id":"2603.23286","ref_index":9,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Physical Knot Classification Beyond Accuracy: A Benchmark and Diagnostic Study","primary_cat":"cs.CV","submitted_at":"2026-03-24T14:50:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"New knot classification benchmark and topology-aware supervision methods yield small specificity gains but confirm that appearance bias remains the dominant failure mode.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2601.06839","ref_index":35,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"PRISM: Color-Stratified Point Cloud Sampling","primary_cat":"cs.CV","submitted_at":"2026-01-11T10:07:03+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"PRISM downsamples point clouds by stratifying on RGB color bins with a maximum capacity k per bin to preserve high chromatic diversity regions over homogeneous surfaces.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2512.17637","ref_index":11,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"About Time: Model-free Reinforcement Learning with Timed Reward Machines","primary_cat":"cs.AI","submitted_at":"2025-12-19T14:39:03+00:00","verdict":"CONDITIONAL","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Timed reward machines extend reward machines with timing constraints, allowing model-free RL algorithms to learn policies that satisfy precise temporal requirements on standard benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2507.13662","ref_index":30,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Iteratively Learning Muscle Memory for Legged Robots to Master Adaptive and High Precision Locomotion","primary_cat":"cs.RO","submitted_at":"2025-07-18T05:13:02+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Integrates iterative learning control with a torque library to enable high-precision adaptive locomotion on bipedal and quadrupedal robots, reducing tracking errors by up to 85% and achieving over 30x faster control rates.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.02587","ref_index":1,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"BEVCALIB: LiDAR-Camera Calibration via Geometry-Guided Bird's-Eye View Representations","primary_cat":"cs.CV","submitted_at":"2025-06-03T08:07:18+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"BEVCALIB performs LiDAR-camera calibration from raw data by fusing camera and LiDAR bird's-eye view features with a novel feature selector and reports state-of-the-art accuracy on KITTI and NuScenes.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2506.00982","ref_index":4,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Robust and Safe Multi-Agent Reinforcement Learning with Communication for Autonomous Vehicles: From Simulation to Hardware","primary_cat":"cs.RO","submitted_at":"2025-06-01T12:29:53+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"RSR-RSMARL is a robust safe MARL framework with V2V communication and CBF safety shields that supports zero-shot sim-to-real transfer and improves coordination on 1/10-scale vehicle hardware.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2505.11771","ref_index":42,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Residual Feature Integration is Sufficient to Prevent Negative Transfer","primary_cat":"cs.LG","submitted_at":"2025-05-17T00:36:59+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Residual feature integration with a trainable target-side encoder provably prevents negative transfer, achieving convergence rates no worse than training from scratch under informative target distributions.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2503.03262","ref_index":98,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Trajectory Prediction for Autonomous Driving: Progress, Limitations, and Future Directions","primary_cat":"cs.RO","submitted_at":"2025-03-05T08:38:51+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"A survey of trajectory prediction techniques for autonomous vehicles that proposes a taxonomy, overviews the prediction pipeline, and highlights remaining research gaps.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"may be prone to errors caused by the incorrect target agent classification by the detector. For vehicles, learning individ- ual behavioral patterns historical data [97] can improve pre- diction accuracy by capturing unique driving styles. Simi- larly, in pedestrian trajectory prediction, appearance cues and posture can offer insights into pedestrians' intentions. Studies [98, 99, 100] have focused on extracting visual cues to capture behavioral patterns to improve prediction accuracy. To estimate posture, two main approaches are employed: using skeleton key-points [52, 101, 102, 103] or leveraging pretrained CNNs [104, 105, 101]. Incorporating additional semantic attributes requires either integrating a subnetwork within the model to extract these at-"},{"citing_arxiv_id":"2410.17517","ref_index":53,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"The Hive Mind is a Single Reinforcement Learning Agent","primary_cat":"cs.MA","submitted_at":"2024-10-23T02:49:37+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Bee hive mind from weighted voter imitation equals a single RL agent using a new multi-armed bandit rule called Maynard-Cross Learning.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2409.01962","ref_index":38,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"Attentive Dilated Convolution for Automatic Sleep Staging using Force-directed Layout","primary_cat":"eess.SP","submitted_at":"2024-08-21T06:35:50+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"AttDiCNN reaches 98.56%, 99.66%, and 99.08% accuracy on EDFX, HMC, and NCH sleep datasets via force-directed visibility graph EEG representations and a three-module attentive dilated CNN architecture.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2210.09114","ref_index":39,"ref_count":1,"confidence":0.9,"is_internal_anchor":false,"paper_title":"INSANE: Cross-Domain UAV Data Sets with Increased Number of Sensors for developing Advanced and Novel Estimators","primary_cat":"cs.RO","submitted_at":"2022-10-17T14:06:17+00:00","verdict":"ACCEPT","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"INSANE releases multiple MAV datasets with cross-environment trajectories, rich multi-IMU and camera suites, high-rate vibration data, and sub-centimeter RTK GNSS ground truth for localization research.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}