A Modular Vision-Language-Action Robotics Framework for Indoor Environments

This paper presents an integrated system for the CMU Vision-Language-Action (VLA) Challenge, designed to enable an autonomous agent to perform complex tasks based on natural language instructions. Our framework employs a modular architecture that orchestrates environment mapping, question processing, and navigation. The system operates in two parallel streams: a perception pipeline that constructs a semantic voxel map from real-time camera feeds using OwlViT embeddings, and a language pipeline that classifies user commands with a Vision-Language Model. The mapping is time-constrained; the system proceeds with a partial map if a 500-second exploration limit is reached. The classified query is then grounded in the geometric and semantic context of the map to generate a detailed prompt for the VLM. This yields an actionable output, demonstrating a capable solution for bridging the gap between human language and robotic action.

LLM-Powered Interactive Robotic Action Synthesis from Multimodal Speech, Gestures, and Music

The quest for intuitive and natural human-robot interaction (HRI) remains a significant challenge in robotics. Traditional methods often rely on rigid, pre-programmed commands that limit the robot's expressiveness and adaptability. This paper introduces a novel framework that leverages the reasoning capabilities of Large Language Models (LLMs) to synthesize complex robotic actions from a rich tapestry of multimodal human inputs: natural speech, hand gestures, and music/sound beats. Our system architecture integrates a speech transcription model, a gesture recognition module, and a signal processing pipeline for beat detection. These processed inputs are contextualized using prompt templates and fed into a LLM. The LLM, informed by a predefined robot action space, reasons over the combined inputs to generate a coherent sequence of actions. This sequence is dispatched to an action queue for execution on a quadruped robot over ROS. The framework has ability to interpret and fuse semantic commands from speech, deictic information from gestures, and rhythmic cues from music. This work represents a step towards creating robots that can interact with humans in a more fluid, creative, and context-aware manner.

Enhancing Efficiency of Quadrupedal Locomotion over Challenging Terrains with Extensible Feet

Recent advancements in legged locomotion research have made legged robots a preferred choice for navigating challenging terrains when compared to their wheeled counterparts. This paper presents a novel locomotion policy, trained using Deep Reinforcement Learning, for a quadrupedal robot equipped with an additional prismatic joint between the knee and foot of each leg. The training is performed in NVIDIA Isaac Gym simulation environment. Our study investigates the impact of these joints on maintaining the quadruped's desired height and following commanded velocities while traversing challenging terrains. We provide comparison results, based on a Cost of Transport (CoT) metric, between quadrupeds with and without prismatic joints. The learned policy is evaluated on a set of challenging terrains using the CoT metric in simulation. Our results demonstrate that the added degrees of actuation offer the locomotion policy more flexibility to use the extra joints to traverse terrains that would be deemed infeasible or prohibitively expensive for the conventional quadrupedal design, resulting in significantly improved efficiency.

A Levy Flight based Narrow Passage Sampling Method for Probabilistic Roadmap Planners

Sampling based probabilistic roadmap planners (PRM) have been successful in motion planning of robots with higher degrees of freedom, but may fail to capture the connectivity of the configuration space in scenarios with a critical narrow passage. In this paper, we show a novel technique based on Levy Flights to generate key samples in the narrow regions of configuration space, which, when combined with a PRM, improves the completeness of the planner. The technique substantially improves sample quality at the expense of a minimal additional computation, when compared with pure random walk based methods, however, still outperforms state of the art random bridge building method, in terms of number of collision calls, computational overhead and sample quality. The method is robust to the changes in the parameters related to the structure of the narrow passage, thus giving an additional generality. A number of 2D & 3D motion planning simulations are presented which shows the effectiveness of the method.