Video Friday: An Earthbound Mars Rover for the Moon

2026-07-03 · Source: IEEE Spectrum · Field: Technology & Digital — Robotics & Autonomous Systems, Artificial Intelligence & Machine Learning · Depth: Intermediate, medium

Summary

This week's robotics brief highlights diverse advancements and upcoming events. NASA is considering the PROMISE mission concept, adapting Curiosity and Perseverance Mars rover designs for a nuclear-powered Moon rover at the South Pole. New robot launches include Weave Robotics' Isaac 1, available for \$500 per month with teleoperation, and Apptronik's Apollo 2, training at its 90,000-square-foot "Robot Park" facility. Humanoid robot developments feature UBTech's lifelike companion robots with "emotional AI" for homes, Flexion's pursuit of general-purpose intelligence, and Figure's ongoing challenges with basic tasks. Innovations include Georgia Tech's Spherephones for spatial audio awareness in human-robot collaboration, KinetIQ Ascend's reinforcement learning for 99.9% manipulation reliability, and soft, lightweight indoor companion robots. Dr. Sebastian Scherer emphasizes field robotics for "dirty, dull, and dangerous" tasks, while a note on ElliQ cautions against equating robot companionship with human interaction. Key 2026 conferences like RSS, IROS, and ICRA are also announced.

Key takeaway

For robotics engineers and AI scientists navigating the evolving landscape, prioritize developing robust, adaptable systems for specialized environments like lunar exploration or hazardous field work. While humanoid robots show promise, recognize current limitations in general dexterity and industrial safety, and critically evaluate claims of "emotional AI" for companionship. Consider integrating advanced perception, like spatial audio, and high-reliability manipulation techniques to enhance human-robot collaboration and task autonomy.

Key insights

Robotics is advancing towards more autonomous, human-centric, and specialized applications, yet significant challenges remain in reliability and social integration.

Principles

• Leverage existing, flight-proven designs for new mission concepts.
• Prioritize safety and social acceptance for indoor companion robots.
• Focus on robust field robotics for dirty, dull, and dangerous tasks.

Method

Reinforcement learning can achieve 99.9% manipulation reliability at human speed; computer vision and visual servoing enable interactive robot serving.

In practice

• Adapt Mars rover testbed designs for lunar exploration missions.
• Consider soft, touch-safe designs for indoor companion robots.
• Explore spatial audio wearables for enhanced human-robot collaboration.

Topics

• Lunar Robotics
• Humanoid Robots
• Field Robotics
• Robot Manipulation
• Companion Robotics
• Robotics Conferences

Best for: Robotics Engineer, AI Scientist, AI Student

Related on AIssential

• Video Friday: Humanoid Learns Tennis Skills Playing Humans — Robotics research is advancing dexterous manipulation, sustainable design, and complex locomotion through AI and novel hardware.
• Will Robotics Have a ChatGPT Moment? — General-purpose robotics will advance through coordinated AI systems and extensive real-world experience, not a single breakthrough.
• What are the Top Humanoid Robots? — AI significantly enhances humanoid robots' capabilities in interaction, realism, and physical agility.
• NASA’s Perseverance rover completes the first AI-planned drive on Mars — AI-planned drives on Mars demonstrate advanced autonomous navigation for deep space exploration.
• Forrester’s First-Ever Humanoid Robot Report Is Here — Humanoid robots are transitioning to commercial viability, driven by AI advancements and cost reductions.
• Why Do Humanoid Robots Still Struggle With the Small Stuff? — Despite AI advancements, humanoid robots still struggle with fundamental physics like force control for reliable real-world interaction.

Open in AIssential →

Editorial summary, takeaway, and curation by AIssential. Original article published by IEEE Spectrum.