New Framework Enables Humanoid Robots to Track Foothold Placement Accurately in Complex Environments
Researchers have introduced a lightweight reinforcement learning framework called 'Mind Your Steps' that trains humanoid robots to accurately track and place their feet on specific target positions in complex environments. Existing approaches either lack explicit foothold control—risking unsafe behaviors like stepping on people—or rely on staged pipelines tied to specific tasks and unrealistic state assumptions. The framework, accepted to RSS 2026, could advance humanoid robots' ability to navigate safely and perform manipulation tasks in real-world settings.
A team of researchers has developed a general-purpose reinforcement learning framework for training humanoid robots to precisely track 3D foothold targets, addressing a key limitation in current locomotion systems. Velocity-commanded policies, while robust, do not explicitly control where a robot places its feet, which can lead to unsafe or imprecise behavior. The new approach uses a dynamic goal sampler to provide footstep support during training, making the learned policy terrain-agnostic rather than tied to specific environments or downstream tasks. A novel target representation is also introduced to handle real-world challenges such as noisy pose estimation and unreliable foot contact sensing. The policy is designed as a standalone low-level controller that can interface with various high-level foothold planners, making it modular and broadly applicable. Experiments in both simulation and real-world settings demonstrate natural and accurate locomotion in challenging conditions. The authors suggest the framework paves the way for combined locomotion and manipulation tasks in complex environments, with the paper accepted to the Robotics: Science and Systems (RSS) 2026 conference.
What's missing
The abstract does not provide quantitative benchmarks comparing performance against prior foothold-tracking methods, nor does it address the framework's computational cost, latency in real-time deployment, or failure modes under extreme perturbations.
What different sources said
- arXiv cs.AICenter
CoRe-MoE: Contrastive Reweighted Mixture of Experts for Multi-Terrain Humanoid Locomotion with Gait Adaptation
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.