In autonomous driving, Bird's-Eye View (BEV) representations provide a structured, top-down abstraction of the vehicle's surroundings and have become a key input modality for Behavioral Cloning (BC) policies. While ground-truth BEV maps are readily available in simulation, real-world deployment requires replacing them...
Felipe Dos Santos, Eric A. Antonelo, Gustavo Claudio Karl Couto· 0 citations
Context-dependent consequence modelling provides a principled mechanism for allocating conservatism by physical risk in autonomous robot navigation failure prediction as consequence-sensitive forecasting.
The proposed situation identification approach enables efficient sensor data management by prioritizing relevant data to the current traffic situation by identifying the current traffic situation using Bird's-Eye-View images.
This work formalises CDPs using a goal-conditioned policy divergence measure and incorporates them into a Receding-Horizon Planner that explores future action sequences while optimizing a cost function balancing task progress and information gain.
Debasmita Ghose, Oz Gitelson, Michael A. Lewkowicz et al.· Autonomous Robots· 1 citation
Reach audiences
Advertise in front of researchers, engineers, and readers.
PlannerForge is presented, an LLM-agent framework that extends all scenario-based testing stages (from Scenario Generation to ADS Assessment) and adds two further LLM-enhanced stages: ADS Enhancement and ADS Benchmarking.
Yuan Gao, Sebastian Müller, Mattia Piccinini et al.· 1 citation
Reward-free latent world models plan by scoring candidate actions with distances in a frozen latent space: an action is preferred if its predicted future embedding lands closer to the goal embedding. This silently assumes that latent closeness is action-rankable, i.e., that ordering candidates by latent distance agrees...
The potential of augmented reality head-mounted displays (AR-HMDs) to address the gap in coordination by facilitating the active maintenance of shared understanding regarding tasks, patient state, responsibilities, and ongoing clinical activity is investigated.
This work shows that paraphrase robustness is a core requirement for reliable VLM-based reward modeling in robotics and introduces ROBORMBENCH, a benchmark with 2,390 real-robot trajectories, ground-truth progress labels, and 21,673 verified paraphrases spanning lexical, syntactic, and action-goal rewrites.
Wonje Jeung, Sangyeon Yoon, Hyesoo Hong et al.· 0 citations
This work proposes SCRIPT, a scalable diffusion policy with a multi-stage training framework for language-driven physics-based humanoid control, and introduces a nonlinear history conditioning mechanism, which preserves the dense recent context and samples increasingly sparse cues from long-term history.
Jingyan Zhang, Han Liang, Rui-Chi Zhang et al.· arXiv.org· 5 citations· ⚡2
Visual reinforcement learning is appealing for robotics but expensive. Off-policy methods are sample-efficient yet slow while on-policy methods parallelize well but waste samples. Recent work has shown that off-policy methods can train faster than on-policy methods in wall-clock time for state-based control. Extending...
Abdulaziz Almuzairee, Henrik I. Christensen· 0 citations
A resilient communication-aware remote robotic control framework based on coupled control and wireless Joint Embedding Predictive Architecture (JEPA) world models that jointly capture robot dynamics and wireless channel evolution from visual observations and a combination of raw and structured radio frequency (RF) repr...
H. Madushanka, Sumudu Samarakoon, Mehdi Bennis· 0 citations
Octopus, a hardware onboarding framework in which a coding agent, rather than a shipped integration, is the runtime that produces the required infrastructure, is presented.
Quilee Simeon, Justin M. Wei, Yile Fan· arXiv.org· 0 citations
A new system identifies and corrects unreliable object descriptions stored in a robot’s memory, improving the robot’s ability to interact with its environment.
Robots are getting smarter, but how can their hardware match that growth? New Microsoft Research findings show that moving AI inference beyond the robot can improve task success, boost efficiency, and support more advanced physical AI workloads. The post Offloaded inference for real-world physical AI robotics appeared first on Microsoft Research.
