#IROS 2026 (8)

RoboParty RP1 Takes on the IROS 2026 Kick-Me Challenge

@techniahqrobot · 227 views · 2026-10-08

HumanoidDisturbance RecoveryReinforcement Learning

LT-Mem: Volatility-Aware Spatio-Temporal Memory for Lifelong Scene Understanding

DGIST team, accepted to IROS 2026. Robots operating long-term revisit evolving environments; existing systems either overwrite history to keep an up-to-date map or store semantic snapshots without cross-session object identity — the authors call this temporal amnesia: unable to answer "Where has the green chair been across all sessions?" LT-Mem is a three-layer solution: (1) Perception: MASt3R-SLAM multi-session alignment (Sim(3) anchors + inter-session loop closures + joint g2o optimization) plus SAM3 instance segmentation extracting per-object centroid/volume/visual embedding; (2) Reasoning: five evidence scores (E1 spatial proximity, E2 temporal continuity, E3 feature similarity as the primary signal w=0.45, E4 motion consistency, E5 occlusion handling) drive deterministic cross-session re-identification, with a constrained LLM judge only for ambiguous cases (MATCH/NEW-TRACK/HOLD); a structural integrity check triggers a session-wide HOLD on alignment failure; a volatility score V accumulates evidence in a Bayesian manner (Eq.2, one-time LLM prior), selecting among OVERWRITE/HOLD/MULTI-HYPOTHESIS updates; (3) Tri-Memory: Live stores current states, Delta logs timestamped events (APPEAR/DISAPPEAR/MOVE/RE-APPEAR/NONE), Meta accumulates volatility statistics feeding back into the update policy. The paper releases LT-VQA (two indoor envs, 10 objects × 10 sessions each, plus an outdoor parking lot over 10 sessions; 61 state-change events and 80 QA pairs). Results: Event F1 0.910 / QA-Event 0.820 / QA-Freq 0.600, beating Geometric/Text-Batch/VLM-Batch/STAR baselines across the board, with 438K tokens — 1/16 of VLM-Batch (7,114K) and 1/100 of STAR (45,859K); swapping in Qwen2.5-3B still reaches 0.885, showing the gains come from the structured memory architecture rather than LLM capacity. Ablations: removing re-identification collapses F1 to 0.140; removing volatility-awareness drops it to 0.615. Scene-level statistics on the parking lot even answer "when should I go to find a parking spot" (8:00 AM, 0 cars vs 1:03 PM, 34 cars).

Yumin Lee, Hyoseok Ju, Giseop Kim · 415 views · Aug 19, 2026

SLAMLong-Term-AutonomyScene UnderstandingAug 19, 2026

1:18

Lumos NIX at IROS 2026: the 89 cm mini humanoid betting that cute is the differentiator — companionship and entertainment as an underrated market

@irvinxyz · 490 views · 2026-09-30

HumanoidIROS 2026Lumos Robotics

0:07

IROS 2026 floor demo: Astribot S1 repeatedly picks and places items from a soft bag

@FluffyHernia · 457 views · 2026-09-28

AstribotAstribot S1IROS 2026

0:12

IROS 2026 Workshop on Athletic Humanoid Robotics: Dance Demos and an Open-Problems Panel

@ZiyunClaudeWang · 1k views · 2026-09-27

IROS 2026HumanoidAthletic Robotics

1:13

Matrix Inno brings tactile data gloves to IROS

@moxianmxkj · 715 views · 2026-09-24

Tactile SensingData CollectionWearable Sensor

IMLE-VLA: Fast Single-Step Action Generation for Vision-Language-Action Policies

Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design couples this backbone with a dedicated continuous action head trained via diffusion or flow matching. However, such heads rely on iterative multi-step sampling, for example 10 Euler steps in π_0.5. This creates an inference bottleneck that produces stop-and-go movement in the robot and slower task completion. We introduce IMLE-VLA, which replaces the iterative action head with a single-step conditional generator trained via conditional Implicit Maximum Likelihood Estimation (cIMLE). The cIMLE objective promotes multimodal action coverage, avoiding the mode collapse of naive regression heads while eliminating multi-step sampling entirely. When IMLE-VLA is applied to π_0.5, it increases inference frequency 3.67x (55 Hz vs. 15 Hz), enabling up to 11x higher action throughput. On the 40-task LIBERO benchmark, IMLE-VLA achieves the highest average success rate (98.0%) among all baselines while leading in inference frequency. Under the test-time perturbations of LIBERO-plus, IMLE-VLA retains π_0.5's robustness while other baselines degrade sharply, confirming that the cIMLE head preserves generalization. Real-world experiments on a Franka Emika Panda across four tasks demonstrate smoother motion (2.2x to 3.0x lower jerk) and faster task completion, with IMLE-VLA outperforming π_0.5 on every task and reducing average VLA inference time per episode by 3.9x to 6.6x. Videos and code are available at https://kianhk6.github.io/IMLE-VLA/

Hosseinkhani, Kian, Peng, Qinhe, Shramko, George · 908 views · Sep 10, 2026

VLAEfficient InferenceSingle-Step Action GenerationSep 10, 2026

1:10

Inflatable Baymax Costume as Whole-Body Robotic Skin

@lukas_m_ziegler · 575 views · 2026-08-31

BaymaxInflatable Skinwhole-body touch

As an Amazon Associate, we earn from qualifying purchases.