MM-ABC Enables Robots to Perform Mobile Manipulation Tasks
Overview
Researchers from HKUST (Guangzhou), Tsinghua University, and others propose MM-ABC, a foundational model for mobile manipulation. The system integrates multi-layer visual perception, future geometric prediction supervision, and coordinated arm-base control to address challenges in simultaneous navigation and operation. In benchmarks like EBench and RoboCasa365, it achieves higher success rates than prior methods, demonstrating improved performance on composite tasks requiring both movement and fine motor skills.
Generated from attributed reports · Updated 2 hours ago
Event evidence and corrections
0 attributed source owners. Ownership does not establish independent confirmation. Quantities are reported separately and are never added together.
Reported quantity · Reported success rate: 32.8 percent · reported trials · Differing source assertions
“如果不采用清晰动作预测，而是坚持用速度预测，论文的消融实验显示，在RoboCasa365基准测试的复合任务上，成功率会从32.8%直接掉到29.2%，掉了3.6个百分点。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 29.2 percent · reported trials · Differing source assertions
“如果不采用清晰动作预测，而是坚持用速度预测，论文的消融实验显示，在RoboCasa365基准测试的复合任务上，成功率会从32.8%直接掉到29.2%，掉了3.6个百分点。”
Exact source · revision 2Source owner not reported
Reported quantity · Reported success rate: 24.9 percent · reported trials · Differing source assertions
“消融实验证明了这一点:去掉这个未来监督分支后，成功率从32.8%掉到24.9%，足足掉了7.9个百分点，这是论文所有消融实验里降幅最大的一项。”
Exact source · revision 2Source owner not reported
Report timeline
Follow attributed reports and material updates.
- Chinese robotics — Dataset and collection discoverySignalMM-ABC Enables Robots to Perform Mobile Manipulation Tasks
Researchers from HKUST (Guangzhou), Tsinghua University, and others propose MM-ABC, a foundational model for mobile manipulation. The system integrates multi-layer visual perception, future geometric prediction supervision, and coordinated arm-base control to address challenges in simultaneous navigation and operation. In benchmarks like EBench and RoboCasa365, it achieves higher success rates than prior methods, demonstrating improved performance on composite tasks requiring both movement and fine motor skills.
Event coverage history
Current attention 4·Peak within the comparable range 5（2026-11-03 22:00 UTC）·Change within the comparable range over 24 hours –
The trend compares participants observed continuously; its scope may be narrower than current attention totals. Hover or click to explore hourly observations, or use the left and right arrow keys.
Timezone · UTC
Article dates follow your selected timezone. Briefing editions use Hong Kong time (UTC+8).